diff options
Diffstat (limited to 'llvm/test/Analysis')
| -rw-r--r-- | llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll | 744 | ||||
| -rw-r--r-- | llvm/test/Analysis/ScalarEvolution/ptrtoaddr.ll | 135 | ||||
| -rw-r--r-- | llvm/test/Analysis/ScalarEvolution/ptrtoint.ll | 20 | ||||
| -rw-r--r-- | llvm/test/Analysis/ScalarEvolution/trip-multiple-guard-info.ll | 28 |
4 files changed, 531 insertions, 396 deletions
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll index 609a23b..0976a10 100644 --- a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll +++ b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll @@ -40,50 +40,50 @@ declare <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x define void @vector_insert_extract_idxzero_128b() #1 { ; CHECK-VSCALE-1-LABEL: 'vector_insert_extract_idxzero_128b' -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; CHECK-VSCALE-2-LABEL: 'vector_insert_extract_idxzero_128b' -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract_idxzero_128b' -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; - %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0) - %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0) - %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0) - %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0) - %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0) - %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0) - %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0) - %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0) - %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0) + %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> poison, i64 0) + %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> poison, i64 0) + %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0) + %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0) + %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0) + %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0) + %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0) + %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0) + %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0) ret void } declare <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float>, <4 x float>, i64) @@ -97,50 +97,50 @@ declare <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x define void @vector_insert_extract_idxzero_256b() #2 { ; CHECK-VSCALE-1-LABEL: 'vector_insert_extract_idxzero_256b' -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> poison, <16 x i16> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; CHECK-VSCALE-2-LABEL: 'vector_insert_extract_idxzero_256b' -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> poison, <16 x i16> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract_idxzero_256b' -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> poison, <16 x i16> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; - %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0) - %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nx4f32(<vscale x 4 x float> undef, i64 0) - %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0) - %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0) - %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0) - %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0) - %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0) - %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0) - %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0) + %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> poison, <16 x i16> poison, i64 0) + %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nx4f32(<vscale x 4 x float> poison, i64 0) + %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0) + %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0) + %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0) + %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0) + %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0) + %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0) + %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0) ret void } declare <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16>, <16 x i16>, i64) @@ -148,157 +148,157 @@ declare <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float>, i64 define void @reductions(<vscale x 4 x i32> %v0, <vscale x 4 x i64> %v1, <vscale x 4 x float> %v2, <vscale x 4 x double> %v3) { ; CHECK-VSCALE-1-LABEL: 'reductions' -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:3 CodeSize:3 Lat:5 SizeLat:3 for: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; CHECK-VSCALE-2-LABEL: 'reductions' -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:3 CodeSize:3 Lat:5 SizeLat:3 for: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; TYPE_BASED_ONLY-LABEL: 'reductions' -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:3 CodeSize:3 Lat:5 SizeLat:3 for: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; - %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef) + %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> poison) %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0) %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1) - %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef) + %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> poison) %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0) %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1) - %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef) + %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> poison) %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0) %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1) - %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef) + %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> poison) %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0) %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1) - %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef) + %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> poison) %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0) %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1) - %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef) + %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> poison) %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0) %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1) - %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef) + %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> poison) %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0) %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1) - %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef) + %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> poison) %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0) %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1) - %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef) + %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> poison) %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0) %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1) - %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.0, <vscale x 1 x float> undef) + %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.0, <vscale x 1 x float> poison) %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.0, <vscale x 4 x float> %v2) %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.0, <vscale x 4 x double> %v3) - %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef) + %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> poison) %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2) %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3) - %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef) + %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> poison) %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2) %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3) @@ -389,123 +389,123 @@ declare <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32>, i1) define void @vector_reverse() #0 { ; CHECK-VSCALE-1-LABEL: 'vector_reverse' -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; CHECK-VSCALE-2-LABEL: 'vector_reverse' -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; TYPE_BASED_ONLY-LABEL: 'vector_reverse' -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; - %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef) - %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> undef) - %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> undef) - %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> undef) - %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> undef) - %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> undef) - %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> undef) - %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> undef) - %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> undef) - %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> undef) - %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> undef) - %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> undef) - %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> undef) - %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> undef) - %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> undef) - %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> undef) - %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> undef) - %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> undef) - %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> undef) - %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef) - %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef) - %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef) - %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef) - %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> undef) - %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> undef) - %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> undef) - %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> undef) + %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> poison) + %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> poison) + %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> poison) + %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> poison) + %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> poison) + %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> poison) + %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> poison) + %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> poison) + %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> poison) + %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> poison) + %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> poison) + %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> poison) + %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> poison) + %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> poison) + %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> poison) + %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> poison) + %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> poison) + %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> poison) + %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> poison) + %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> poison) + %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> poison) + %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> poison) + %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> poison) + %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> poison) + %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> poison) + %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> poison) + %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> poison) ret void } declare <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8>) @@ -912,158 +912,158 @@ declare <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double>, define void @get_lane_mask() #0 { ; CHECK-VSCALE-1-LABEL: 'get_lane_mask' -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 poison, i16 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 poison, i16 poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; CHECK-VSCALE-2-LABEL: 'get_lane_mask' -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 poison, i16 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 poison, i32 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 poison, i64 poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 poison, i16 poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; TYPE_BASED_ONLY-LABEL: 'get_lane_mask' -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 poison, i32 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 poison, i32 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 poison, i32 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 poison, i32 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 poison, i16 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 poison, i32 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 poison, i32 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 poison, i32 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 poison, i32 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 poison, i64 poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 poison, i16 poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; - %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef) - %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef) - %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef) - %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef) + %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 poison, i64 poison) + %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 poison, i64 poison) + %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 poison, i64 poison) + %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 poison, i64 poison) - %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef) - %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef) - %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef) - %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef) + %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 poison, i32 poison) + %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 poison, i32 poison) + %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 poison, i32 poison) + %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 poison, i32 poison) - %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef) - %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef) + %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 poison, i64 poison) + %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 poison, i16 poison) - %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef) - %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef) - %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef) - %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef) + %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 poison, i64 poison) + %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 poison, i64 poison) + %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 poison, i64 poison) + %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 poison, i64 poison) - %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef) - %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef) - %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef) - %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef) + %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 poison, i32 poison) + %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 poison, i32 poison) + %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 poison, i32 poison) + %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 poison, i32 poison) - %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef) - %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef) + %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 poison, i64 poison) + %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 poison, i16 poison) ret void } define void @fshr() #0 { ; CHECK-VSCALE-1-LABEL: 'fshr' -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; CHECK-VSCALE-2-LABEL: 'fshr' -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; TYPE_BASED_ONLY-LABEL: 'fshr' -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; - call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef) - call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef) - call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef) - call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef) + call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison) + call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison) + call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison) + call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison) ret void } define void @fshl() #0 { ; CHECK-VSCALE-1-LABEL: 'fshl' -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; CHECK-VSCALE-2-LABEL: 'fshl' -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; TYPE_BASED_ONLY-LABEL: 'fshl' -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; - call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef) - call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef) - call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef) - call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef) + call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison) + call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison) + call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison) + call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison) ret void } @@ -1362,48 +1362,48 @@ define void @histogram_nxv4i64(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %m define void @match() #3 { ; CHECK-VSCALE-1-LABEL: 'match' -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef) -; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> poison, <vscale x 16 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> poison, <vscale x 8 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> poison, <vscale x 4 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> poison, <vscale x 2 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> poison, <16 x i8> poison, <16 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> poison, <8 x i16> poison, <8 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> poison, <4 x i32> poison, <4 x i1> poison) +; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> poison, <2 x i64> poison, <2 x i1> poison) ; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; CHECK-VSCALE-2-LABEL: 'match' -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef) -; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> poison, <vscale x 16 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> poison, <vscale x 8 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> poison, <vscale x 4 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> poison, <vscale x 2 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> poison, <16 x i8> poison, <16 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> poison, <8 x i16> poison, <8 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> poison, <4 x i32> poison, <4 x i1> poison) +; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> poison, <2 x i64> poison, <2 x i1> poison) ; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; ; TYPE_BASED_ONLY-LABEL: 'match' -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef) -; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> poison, <vscale x 16 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> poison, <vscale x 8 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> poison, <vscale x 4 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> poison, <vscale x 2 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> poison, <16 x i8> poison, <16 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> poison, <8 x i16> poison, <8 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> poison, <4 x i32> poison, <4 x i1> poison) +; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> poison, <2 x i64> poison, <2 x i1> poison) ; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void ; - %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef) - %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef) - %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef) - %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef) + %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> poison, <vscale x 16 x i1> poison) + %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> poison, <vscale x 8 x i1> poison) + %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> poison, <vscale x 4 x i1> poison) + %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> poison, <vscale x 2 x i1> poison) - %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef) - %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef) - %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef) - %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef) + %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> poison, <16 x i8> poison, <16 x i1> poison) + %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> poison, <8 x i16> poison, <8 x i1> poison) + %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> poison, <4 x i32> poison, <4 x i1> poison) + %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> poison, <2 x i64> poison, <2 x i1> poison) ret void } diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoaddr.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoaddr.ll new file mode 100644 index 0000000..ebab9f0 --- /dev/null +++ b/llvm/test/Analysis/ScalarEvolution/ptrtoaddr.ll @@ -0,0 +1,135 @@ +; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py +; RUN: opt < %s --data-layout="e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" -S -disable-output -disable-verify "-passes=print<scalar-evolution>" 2>&1 | FileCheck --check-prefixes=ALL,X64 %s +; RUN: opt < %s --data-layout="e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-f64:32:64-f80:32-n8:16:32-S128" -S -disable-output -disable-verify "-passes=print<scalar-evolution>" 2>&1 | FileCheck --check-prefixes=ALL,X32 %s + +declare void @useptr(ptr) + +define void @ptrtoaddr(ptr %in, ptr %out0, ptr %out1, ptr %out2, ptr %out3) { +; X64-LABEL: 'ptrtoaddr' +; X64-NEXT: Classifying expressions for: @ptrtoaddr +; X64-NEXT: %p0 = ptrtoaddr ptr %in to i64 +; X64-NEXT: --> %p0 U: full-set S: full-set +; X64-NEXT: %p1 = ptrtoaddr ptr %in to i32 +; X64-NEXT: --> %p1 U: full-set S: full-set +; X64-NEXT: %p2 = ptrtoaddr ptr %in to i16 +; X64-NEXT: --> %p2 U: full-set S: full-set +; X64-NEXT: %p3 = ptrtoaddr ptr %in to i128 +; X64-NEXT: --> %p3 U: full-set S: full-set +; X64-NEXT: Determining loop execution counts for: @ptrtoaddr +; +; X32-LABEL: 'ptrtoaddr' +; X32-NEXT: Classifying expressions for: @ptrtoaddr +; X32-NEXT: %p0 = ptrtoaddr ptr %in to i64 +; X32-NEXT: --> %p0 U: full-set S: full-set +; X32-NEXT: %p1 = ptrtoaddr ptr %in to i32 +; X32-NEXT: --> %p1 U: full-set S: full-set +; X32-NEXT: %p2 = ptrtoaddr ptr %in to i16 +; X32-NEXT: --> %p2 U: full-set S: full-set +; X32-NEXT: %p3 = ptrtoaddr ptr %in to i128 +; X32-NEXT: --> %p3 U: full-set S: full-set +; X32-NEXT: Determining loop execution counts for: @ptrtoaddr +; + %p0 = ptrtoaddr ptr %in to i64 + %p1 = ptrtoaddr ptr %in to i32 + %p2 = ptrtoaddr ptr %in to i16 + %p3 = ptrtoaddr ptr %in to i128 + store i64 %p0, ptr %out0 + store i32 %p1, ptr %out1 + store i16 %p2, ptr %out2 + store i128 %p3, ptr %out3 + ret void +} + +define void @ptrtoaddr_as1(ptr addrspace(1) %in, ptr %out0, ptr %out1, ptr %out2, ptr %out3) { +; X64-LABEL: 'ptrtoaddr_as1' +; X64-NEXT: Classifying expressions for: @ptrtoaddr_as1 +; X64-NEXT: %p0 = ptrtoaddr ptr addrspace(1) %in to i64 +; X64-NEXT: --> %p0 U: full-set S: full-set +; X64-NEXT: %p1 = ptrtoaddr ptr addrspace(1) %in to i32 +; X64-NEXT: --> %p1 U: full-set S: full-set +; X64-NEXT: %p2 = ptrtoaddr ptr addrspace(1) %in to i16 +; X64-NEXT: --> %p2 U: full-set S: full-set +; X64-NEXT: %p3 = ptrtoaddr ptr addrspace(1) %in to i128 +; X64-NEXT: --> %p3 U: full-set S: full-set +; X64-NEXT: Determining loop execution counts for: @ptrtoaddr_as1 +; +; X32-LABEL: 'ptrtoaddr_as1' +; X32-NEXT: Classifying expressions for: @ptrtoaddr_as1 +; X32-NEXT: %p0 = ptrtoaddr ptr addrspace(1) %in to i64 +; X32-NEXT: --> %p0 U: full-set S: full-set +; X32-NEXT: %p1 = ptrtoaddr ptr addrspace(1) %in to i32 +; X32-NEXT: --> %p1 U: full-set S: full-set +; X32-NEXT: %p2 = ptrtoaddr ptr addrspace(1) %in to i16 +; X32-NEXT: --> %p2 U: full-set S: full-set +; X32-NEXT: %p3 = ptrtoaddr ptr addrspace(1) %in to i128 +; X32-NEXT: --> %p3 U: full-set S: full-set +; X32-NEXT: Determining loop execution counts for: @ptrtoaddr_as1 +; + %p0 = ptrtoaddr ptr addrspace(1) %in to i64 + %p1 = ptrtoaddr ptr addrspace(1) %in to i32 + %p2 = ptrtoaddr ptr addrspace(1) %in to i16 + %p3 = ptrtoaddr ptr addrspace(1) %in to i128 + store i64 %p0, ptr %out0 + store i32 %p1, ptr %out1 + store i16 %p2, ptr %out2 + store i128 %p3, ptr %out3 + ret void +} + +define void @ptrtoaddr_of_bitcast(ptr %in, ptr %out0) { +; X64-LABEL: 'ptrtoaddr_of_bitcast' +; X64-NEXT: Classifying expressions for: @ptrtoaddr_of_bitcast +; X64-NEXT: %in_casted = bitcast ptr %in to ptr +; X64-NEXT: --> %in U: full-set S: full-set +; X64-NEXT: %p0 = ptrtoaddr ptr %in_casted to i64 +; X64-NEXT: --> %p0 U: full-set S: full-set +; X64-NEXT: Determining loop execution counts for: @ptrtoaddr_of_bitcast +; +; X32-LABEL: 'ptrtoaddr_of_bitcast' +; X32-NEXT: Classifying expressions for: @ptrtoaddr_of_bitcast +; X32-NEXT: %in_casted = bitcast ptr %in to ptr +; X32-NEXT: --> %in U: full-set S: full-set +; X32-NEXT: %p0 = ptrtoaddr ptr %in_casted to i64 +; X32-NEXT: --> %p0 U: full-set S: full-set +; X32-NEXT: Determining loop execution counts for: @ptrtoaddr_of_bitcast +; + %in_casted = bitcast ptr %in to ptr + %p0 = ptrtoaddr ptr %in_casted to i64 + store i64 %p0, ptr %out0 + ret void +} + +define void @ptrtoaddr_of_nullptr(ptr %out0) { +; ALL-LABEL: 'ptrtoaddr_of_nullptr' +; ALL-NEXT: Classifying expressions for: @ptrtoaddr_of_nullptr +; ALL-NEXT: %p0 = ptrtoaddr ptr null to i64 +; ALL-NEXT: --> %p0 U: full-set S: full-set +; ALL-NEXT: Determining loop execution counts for: @ptrtoaddr_of_nullptr +; + %p0 = ptrtoaddr ptr null to i64 + store i64 %p0, ptr %out0 + ret void +} + +define void @ptrtoaddr_of_gep(ptr %in, ptr %out0) { +; X64-LABEL: 'ptrtoaddr_of_gep' +; X64-NEXT: Classifying expressions for: @ptrtoaddr_of_gep +; X64-NEXT: %in_adj = getelementptr inbounds i8, ptr %in, i64 42 +; X64-NEXT: --> (42 + %in) U: full-set S: full-set +; X64-NEXT: %p0 = ptrtoaddr ptr %in_adj to i64 +; X64-NEXT: --> %p0 U: full-set S: full-set +; X64-NEXT: Determining loop execution counts for: @ptrtoaddr_of_gep +; +; X32-LABEL: 'ptrtoaddr_of_gep' +; X32-NEXT: Classifying expressions for: @ptrtoaddr_of_gep +; X32-NEXT: %in_adj = getelementptr inbounds i8, ptr %in, i64 42 +; X32-NEXT: --> (42 + %in) U: full-set S: full-set +; X32-NEXT: %p0 = ptrtoaddr ptr %in_adj to i64 +; X32-NEXT: --> %p0 U: full-set S: full-set +; X32-NEXT: Determining loop execution counts for: @ptrtoaddr_of_gep +; + %in_adj = getelementptr inbounds i8, ptr %in, i64 42 + %p0 = ptrtoaddr ptr %in_adj to i64 + store i64 %p0, ptr %out0 + ret void +} diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll index acac2c9..0c1f37b 100644 --- a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll +++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll @@ -382,7 +382,7 @@ define void @pr46786_c26_char(ptr %arg, ptr %arg1, ptr %arg2) { ; X64-NEXT: %i9 = ptrtoint ptr %i7 to i64 ; X64-NEXT: --> {(ptrtoint ptr %arg to i64),+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable } ; X64-NEXT: %i10 = sub i64 %i9, %i4 -; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable } +; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,-1) S: [0,-1) Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable } ; X64-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10 ; X64-NEXT: --> {%arg2,+,1}<nw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg2) LoopDispositions: { %bb6: Computable } ; X64-NEXT: %i12 = load i8, ptr %i11, align 1 @@ -393,7 +393,7 @@ define void @pr46786_c26_char(ptr %arg, ptr %arg1, ptr %arg2) { ; X64-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg) LoopDispositions: { %bb6: Computable } ; X64-NEXT: Determining loop execution counts for: @pr46786_c26_char ; X64-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) -; X64-NEXT: Loop %bb6: constant max backedge-taken count is i64 -1 +; X64-NEXT: Loop %bb6: constant max backedge-taken count is i64 -2 ; X64-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) ; X64-NEXT: Loop %bb6: Trip multiple is 1 ; @@ -406,9 +406,9 @@ define void @pr46786_c26_char(ptr %arg, ptr %arg1, ptr %arg2) { ; X32-NEXT: %i8 = load i8, ptr %i7, align 1 ; X32-NEXT: --> %i8 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant } ; X32-NEXT: %i9 = ptrtoint ptr %i7 to i64 -; X32-NEXT: --> {(zext i32 (ptrtoint ptr %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934591) S: [0,8589934591) Exits: ((zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) + (zext i32 (ptrtoint ptr %arg to i32) to i64)) LoopDispositions: { %bb6: Computable } +; X32-NEXT: --> {(zext i32 (ptrtoint ptr %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934590) S: [0,8589934590) Exits: ((zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) + (zext i32 (ptrtoint ptr %arg to i32) to i64)) LoopDispositions: { %bb6: Computable } ; X32-NEXT: %i10 = sub i64 %i9, %i4 -; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967296) S: [0,4294967296) Exits: (zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable } +; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967295) S: [0,4294967295) Exits: (zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable } ; X32-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10 ; X32-NEXT: --> {%arg2,+,1}<%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg2) LoopDispositions: { %bb6: Computable } ; X32-NEXT: %i12 = load i8, ptr %i11, align 1 @@ -419,7 +419,7 @@ define void @pr46786_c26_char(ptr %arg, ptr %arg1, ptr %arg2) { ; X32-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg) LoopDispositions: { %bb6: Computable } ; X32-NEXT: Determining loop execution counts for: @pr46786_c26_char ; X32-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) -; X32-NEXT: Loop %bb6: constant max backedge-taken count is i32 -1 +; X32-NEXT: Loop %bb6: constant max backedge-taken count is i32 -2 ; X32-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) ; X32-NEXT: Loop %bb6: Trip multiple is 1 ; @@ -459,7 +459,7 @@ define void @pr46786_c26_char_cmp_ops_swapped(ptr %arg, ptr %arg1, ptr %arg2) { ; X64-NEXT: %i9 = ptrtoint ptr %i7 to i64 ; X64-NEXT: --> {(ptrtoint ptr %arg to i64),+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable } ; X64-NEXT: %i10 = sub i64 %i9, %i4 -; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable } +; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,-1) S: [0,-1) Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable } ; X64-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10 ; X64-NEXT: --> {%arg2,+,1}<nw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg2) LoopDispositions: { %bb6: Computable } ; X64-NEXT: %i12 = load i8, ptr %i11, align 1 @@ -470,7 +470,7 @@ define void @pr46786_c26_char_cmp_ops_swapped(ptr %arg, ptr %arg1, ptr %arg2) { ; X64-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg) LoopDispositions: { %bb6: Computable } ; X64-NEXT: Determining loop execution counts for: @pr46786_c26_char_cmp_ops_swapped ; X64-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) -; X64-NEXT: Loop %bb6: constant max backedge-taken count is i64 -1 +; X64-NEXT: Loop %bb6: constant max backedge-taken count is i64 -2 ; X64-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) ; X64-NEXT: Loop %bb6: Trip multiple is 1 ; @@ -483,9 +483,9 @@ define void @pr46786_c26_char_cmp_ops_swapped(ptr %arg, ptr %arg1, ptr %arg2) { ; X32-NEXT: %i8 = load i8, ptr %i7, align 1 ; X32-NEXT: --> %i8 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant } ; X32-NEXT: %i9 = ptrtoint ptr %i7 to i64 -; X32-NEXT: --> {(zext i32 (ptrtoint ptr %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934591) S: [0,8589934591) Exits: ((zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) + (zext i32 (ptrtoint ptr %arg to i32) to i64)) LoopDispositions: { %bb6: Computable } +; X32-NEXT: --> {(zext i32 (ptrtoint ptr %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934590) S: [0,8589934590) Exits: ((zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) + (zext i32 (ptrtoint ptr %arg to i32) to i64)) LoopDispositions: { %bb6: Computable } ; X32-NEXT: %i10 = sub i64 %i9, %i4 -; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967296) S: [0,4294967296) Exits: (zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable } +; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967295) S: [0,4294967295) Exits: (zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable } ; X32-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10 ; X32-NEXT: --> {%arg2,+,1}<%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg2) LoopDispositions: { %bb6: Computable } ; X32-NEXT: %i12 = load i8, ptr %i11, align 1 @@ -496,7 +496,7 @@ define void @pr46786_c26_char_cmp_ops_swapped(ptr %arg, ptr %arg1, ptr %arg2) { ; X32-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg) LoopDispositions: { %bb6: Computable } ; X32-NEXT: Determining loop execution counts for: @pr46786_c26_char_cmp_ops_swapped ; X32-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) -; X32-NEXT: Loop %bb6: constant max backedge-taken count is i32 -1 +; X32-NEXT: Loop %bb6: constant max backedge-taken count is i32 -2 ; X32-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) ; X32-NEXT: Loop %bb6: Trip multiple is 1 ; diff --git a/llvm/test/Analysis/ScalarEvolution/trip-multiple-guard-info.ll b/llvm/test/Analysis/ScalarEvolution/trip-multiple-guard-info.ll index 7ba422d..a477465c 100644 --- a/llvm/test/Analysis/ScalarEvolution/trip-multiple-guard-info.ll +++ b/llvm/test/Analysis/ScalarEvolution/trip-multiple-guard-info.ll @@ -578,22 +578,22 @@ define void @test_ptr_aligned_by_2_and_4_via_assumption(ptr %start, ptr %end) { ; CHECK-LABEL: 'test_ptr_aligned_by_2_and_4_via_assumption' ; CHECK-NEXT: Classifying expressions for: @test_ptr_aligned_by_2_and_4_via_assumption ; CHECK-NEXT: %iv = phi ptr [ %start, %entry ], [ %iv.next, %loop ] -; CHECK-NEXT: --> {%start,+,4}<%loop> U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Computable } +; CHECK-NEXT: --> {%start,+,4}<%loop> U: [0,-1) S: [-9223372036854775808,9223372036854775807) Exits: <<Unknown>> LoopDispositions: { %loop: Computable } ; CHECK-NEXT: %iv.next = getelementptr i8, ptr %iv, i64 4 -; CHECK-NEXT: --> {(4 + %start),+,4}<%loop> U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Computable } +; CHECK-NEXT: --> {(4 + %start),+,4}<%loop> U: [0,-1) S: [-9223372036854775808,9223372036854775807) Exits: <<Unknown>> LoopDispositions: { %loop: Computable } ; CHECK-NEXT: Determining loop execution counts for: @test_ptr_aligned_by_2_and_4_via_assumption ; CHECK-NEXT: Loop %loop: Unpredictable backedge-taken count. ; CHECK-NEXT: Loop %loop: Unpredictable constant max backedge-taken count. ; CHECK-NEXT: Loop %loop: Unpredictable symbolic max backedge-taken count. ; CHECK-NEXT: Loop %loop: Predicated backedge-taken count is ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4) ; CHECK-NEXT: Predicates: -; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 (ptrtoint ptr %end to i64) to i2) + (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2))) to i64) == 0 +; CHECK-NEXT: Equal predicate: (zext i2 (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2)) to i64) == 0 ; CHECK-NEXT: Loop %loop: Predicated constant max backedge-taken count is i64 4611686018427387903 ; CHECK-NEXT: Predicates: -; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 (ptrtoint ptr %end to i64) to i2) + (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2))) to i64) == 0 +; CHECK-NEXT: Equal predicate: (zext i2 (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2)) to i64) == 0 ; CHECK-NEXT: Loop %loop: Predicated symbolic max backedge-taken count is ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4) ; CHECK-NEXT: Predicates: -; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 (ptrtoint ptr %end to i64) to i2) + (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2))) to i64) == 0 +; CHECK-NEXT: Equal predicate: (zext i2 (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2)) to i64) == 0 ; entry: call void @llvm.assume(i1 true) [ "align"(ptr %start, i64 2) ] @@ -615,9 +615,9 @@ define void @test_ptrs_aligned_by_4_via_assumption(ptr %start, ptr %end) { ; CHECK-LABEL: 'test_ptrs_aligned_by_4_via_assumption' ; CHECK-NEXT: Classifying expressions for: @test_ptrs_aligned_by_4_via_assumption ; CHECK-NEXT: %iv = phi ptr [ %start, %entry ], [ %iv.next, %loop ] -; CHECK-NEXT: --> {%start,+,4}<%loop> U: full-set S: full-set Exits: ((4 * ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4))<nuw> + %start) LoopDispositions: { %loop: Computable } +; CHECK-NEXT: --> {%start,+,4}<%loop> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: (-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64) + %start) LoopDispositions: { %loop: Computable } ; CHECK-NEXT: %iv.next = getelementptr i8, ptr %iv, i64 4 -; CHECK-NEXT: --> {(4 + %start),+,4}<%loop> U: full-set S: full-set Exits: (4 + (4 * ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4))<nuw> + %start) LoopDispositions: { %loop: Computable } +; CHECK-NEXT: --> {(4 + %start),+,4}<%loop> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: ((-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64) + %start) LoopDispositions: { %loop: Computable } ; CHECK-NEXT: Determining loop execution counts for: @test_ptrs_aligned_by_4_via_assumption ; CHECK-NEXT: Loop %loop: backedge-taken count is ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4) ; CHECK-NEXT: Loop %loop: constant max backedge-taken count is i64 4611686018427387903 @@ -644,9 +644,9 @@ define void @test_ptrs_aligned_by_8_via_assumption(ptr %start, ptr %end) { ; CHECK-LABEL: 'test_ptrs_aligned_by_8_via_assumption' ; CHECK-NEXT: Classifying expressions for: @test_ptrs_aligned_by_8_via_assumption ; CHECK-NEXT: %iv = phi ptr [ %start, %entry ], [ %iv.next, %loop ] -; CHECK-NEXT: --> {%start,+,4}<%loop> U: full-set S: full-set Exits: ((4 * ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4))<nuw> + %start) LoopDispositions: { %loop: Computable } +; CHECK-NEXT: --> {%start,+,4}<%loop> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: (-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64) + %start) LoopDispositions: { %loop: Computable } ; CHECK-NEXT: %iv.next = getelementptr i8, ptr %iv, i64 4 -; CHECK-NEXT: --> {(4 + %start),+,4}<%loop> U: full-set S: full-set Exits: (4 + (4 * ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4))<nuw> + %start) LoopDispositions: { %loop: Computable } +; CHECK-NEXT: --> {(4 + %start)<nuw><nsw>,+,4}<%loop> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: ((-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64) + %start) LoopDispositions: { %loop: Computable } ; CHECK-NEXT: Determining loop execution counts for: @test_ptrs_aligned_by_8_via_assumption ; CHECK-NEXT: Loop %loop: backedge-taken count is ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4) ; CHECK-NEXT: Loop %loop: constant max backedge-taken count is i64 4611686018427387903 @@ -677,22 +677,22 @@ define void @test_ptr_aligned_by_4_via_assumption_multiple_loop_predecessors(ptr ; CHECK-NEXT: %c = call i1 @cond() ; CHECK-NEXT: --> %c U: full-set S: full-set ; CHECK-NEXT: %iv = phi ptr [ %start, %then ], [ %start, %else ], [ %iv.next, %loop ] -; CHECK-NEXT: --> {%start,+,4}<%loop> U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Computable } +; CHECK-NEXT: --> {%start,+,4}<%loop> U: [0,-1) S: [-9223372036854775808,9223372036854775807) Exits: <<Unknown>> LoopDispositions: { %loop: Computable } ; CHECK-NEXT: %iv.next = getelementptr i8, ptr %iv, i64 4 -; CHECK-NEXT: --> {(4 + %start),+,4}<%loop> U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Computable } +; CHECK-NEXT: --> {(4 + %start),+,4}<%loop> U: [0,-1) S: [-9223372036854775808,9223372036854775807) Exits: <<Unknown>> LoopDispositions: { %loop: Computable } ; CHECK-NEXT: Determining loop execution counts for: @test_ptr_aligned_by_4_via_assumption_multiple_loop_predecessors ; CHECK-NEXT: Loop %loop: Unpredictable backedge-taken count. ; CHECK-NEXT: Loop %loop: Unpredictable constant max backedge-taken count. ; CHECK-NEXT: Loop %loop: Unpredictable symbolic max backedge-taken count. ; CHECK-NEXT: Loop %loop: Predicated backedge-taken count is ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4) ; CHECK-NEXT: Predicates: -; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 (ptrtoint ptr %end to i64) to i2) + (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2))) to i64) == 0 +; CHECK-NEXT: Equal predicate: (zext i2 (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2)) to i64) == 0 ; CHECK-NEXT: Loop %loop: Predicated constant max backedge-taken count is i64 4611686018427387903 ; CHECK-NEXT: Predicates: -; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 (ptrtoint ptr %end to i64) to i2) + (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2))) to i64) == 0 +; CHECK-NEXT: Equal predicate: (zext i2 (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2)) to i64) == 0 ; CHECK-NEXT: Loop %loop: Predicated symbolic max backedge-taken count is ((-4 + (-1 * (ptrtoint ptr %start to i64)) + (ptrtoint ptr %end to i64)) /u 4) ; CHECK-NEXT: Predicates: -; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 (ptrtoint ptr %end to i64) to i2) + (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2))) to i64) == 0 +; CHECK-NEXT: Equal predicate: (zext i2 (-1 * (trunc i64 (ptrtoint ptr %start to i64) to i2)) to i64) == 0 ; entry: call void @llvm.assume(i1 true) [ "align"(ptr %start, i64 2) ] |