diff options
Diffstat (limited to 'llvm/test/CodeGen/DirectX')
7 files changed, 52 insertions, 72 deletions
diff --git a/llvm/test/CodeGen/DirectX/ShaderFlags/lifetimes-noint64op.ll b/llvm/test/CodeGen/DirectX/ShaderFlags/lifetimes-noint64op.ll deleted file mode 100644 index 736c86e..0000000 --- a/llvm/test/CodeGen/DirectX/ShaderFlags/lifetimes-noint64op.ll +++ /dev/null @@ -1,36 +0,0 @@ -; RUN: opt -S --passes="print-dx-shader-flags" 2>&1 %s | FileCheck %s -; RUN: llc %s --filetype=obj -o - | obj2yaml | FileCheck %s --check-prefix=DXC - -target triple = "dxil-pc-shadermodel6.7-library" - -; CHECK: ; Combined Shader Flags for Module -; CHECK-NEXT: ; Shader Flags Value: 0x00000000 -; CHECK-NEXT: ; -; CHECK-NOT: ; Note: shader requires additional functionality: -; CHECK-NOT: ; 64-Bit integer -; CHECK-NOT: ; Note: extra DXIL module flags: -; CHECK-NOT: ; -; CHECK-NEXT: ; Shader Flags for Module Functions -; CHECK-NEXT: ; Function lifetimes : 0x00000000 - -define void @lifetimes() #0 { - %a = alloca [4 x i32], align 8 - call void @llvm.lifetime.start.p0(i64 16, ptr nonnull %a) - call void @llvm.lifetime.end.p0(i64 16, ptr nonnull %a) - ret void -} - -; Function Attrs: nounwind memory(argmem: readwrite) -declare void @llvm.lifetime.start.p0(i64, ptr) #1 - -; Function Attrs: nounwind memory(argmem: readwrite) -declare void @llvm.lifetime.end.p0(i64, ptr) #1 - -attributes #0 = { convergent norecurse nounwind "hlsl.export"} -attributes #1 = { nounwind memory(argmem: readwrite) } - -; DXC: - Name: SFI0 -; DXC-NEXT: Size: 8 -; DXC-NOT: Flags: -; DXC-NOT: Int64Ops: true -; DXC: ... diff --git a/llvm/test/CodeGen/DirectX/UAddc.ll b/llvm/test/CodeGen/DirectX/UAddc.ll index 4b46b56..dd7aa23 100644 --- a/llvm/test/CodeGen/DirectX/UAddc.ll +++ b/llvm/test/CodeGen/DirectX/UAddc.ll @@ -35,14 +35,10 @@ define noundef <2 x i32> @test_UAddc_vec2(<2 x i32> noundef %a, <2 x i32> nounde ; CHECK-NEXT: [[UADDC_I1:%.*]] = call [[DX_TYPES_I32C]] @dx.op.binaryWithCarryOrBorrow.i32(i32 44, i32 [[A_I1]], i32 [[B_I1]]) #[[ATTR0]] ; CHECK-NEXT: [[CARRY_ELEM0:%.*]] = extractvalue [[DX_TYPES_I32C]] [[UADDC_I0]], 1 ; CHECK-NEXT: [[CARRY_ELEM1:%.*]] = extractvalue [[DX_TYPES_I32C]] [[UADDC_I1]], 1 -; CHECK-NEXT: [[CARRY_UPTO0:%.*]] = insertelement <2 x i1> poison, i1 [[CARRY_ELEM0]], i64 0 -; CHECK-NEXT: [[CARRY:%.*]] = insertelement <2 x i1> [[CARRY_UPTO0]], i1 [[CARRY_ELEM1]], i64 1 -; CHECK-NEXT: [[CARRY_I0:%.*]] = extractelement <2 x i1> [[CARRY]], i64 0 -; CHECK-NEXT: [[CARRY_I1:%.*]] = extractelement <2 x i1> [[CARRY]], i64 1 ; CHECK-NEXT: [[SUM_ELEM0:%.*]] = extractvalue [[DX_TYPES_I32C]] [[UADDC_I0]], 0 ; CHECK-NEXT: [[SUM_ELEM1:%.*]] = extractvalue [[DX_TYPES_I32C]] [[UADDC_I1]], 0 -; CHECK-NEXT: [[CARRY_ZEXT_I0:%.*]] = zext i1 [[CARRY_I0]] to i32 -; CHECK-NEXT: [[CARRY_ZEXT_I1:%.*]] = zext i1 [[CARRY_I1]] to i32 +; CHECK-NEXT: [[CARRY_ZEXT_I0:%.*]] = zext i1 [[CARRY_ELEM0]] to i32 +; CHECK-NEXT: [[CARRY_ZEXT_I1:%.*]] = zext i1 [[CARRY_ELEM1]] to i32 ; CHECK-NEXT: [[RESULT_I0:%.*]] = add i32 [[SUM_ELEM0]], [[CARRY_ZEXT_I0]] ; CHECK-NEXT: [[RESULT_I1:%.*]] = add i32 [[SUM_ELEM1]], [[CARRY_ZEXT_I1]] ; CHECK-NEXT: [[RESULT_UPTO0:%.*]] = insertelement <2 x i32> poison, i32 [[RESULT_I0]], i64 0 diff --git a/llvm/test/CodeGen/DirectX/flatten-array.ll b/llvm/test/CodeGen/DirectX/flatten-array.ll index 1376a1d..a2e1055 100644 --- a/llvm/test/CodeGen/DirectX/flatten-array.ll +++ b/llvm/test/CodeGen/DirectX/flatten-array.ll @@ -218,6 +218,28 @@ define void @two_index_gep_const() { ret void } +define void @zero_index_global() { + ; CHECK-LABEL: define void @zero_index_global( + ; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [4 x float], ptr addrspace(3) @g.1dim, i32 0, i32 0 + ; CHECK-NEXT: load float, ptr addrspace(3) [[GEP]], align 4 + ; CHECK-NEXT: ret void + %1 = getelementptr inbounds nuw [2 x [2 x float]], ptr addrspace(3) @g, i32 0, i32 0, i32 0 + %2 = load float, ptr addrspace(3) %1, align 4 + ret void +} + +; Note: A ConstantExpr GEP with all 0 indices is equivalent to the pointer +; operand of the GEP. Therefore the visitLoadInst will not see the pointer operand +; as a ConstantExpr GEP and will not create a GEP instruction to be visited. +; The later dxil-legalize pass will insert a GEP in this instance. +define void @zero_index_global_const() { + ; CHECK-LABEL: define void @zero_index_global_const( + ; CHECK-NEXT: load float, ptr addrspace(3) @g.1dim, align 4 + ; CHECK-NEXT: ret void + %1 = load float, ptr addrspace(3) getelementptr inbounds nuw ([2 x [2 x float]], ptr addrspace(3) @g, i32 0, i32 0, i32 0), align 4 + ret void +} + define void @gep_4d_index_test() { ; CHECK-LABEL: gep_4d_index_test ; CHECK: [[a:%.*]] = alloca [16 x i32], align 4 diff --git a/llvm/test/CodeGen/DirectX/legalize-lifetimes-valver-1.6.ll b/llvm/test/CodeGen/DirectX/legalize-lifetimes-valver-1.6.ll index f77df2d..6552ccd 100644 --- a/llvm/test/CodeGen/DirectX/legalize-lifetimes-valver-1.6.ll +++ b/llvm/test/CodeGen/DirectX/legalize-lifetimes-valver-1.6.ll @@ -1,6 +1,5 @@ ; RUN: opt -S -passes='dxil-op-lower' -mtriple=dxil-pc-shadermodel6.3-library %s | FileCheck %s --check-prefixes=CHECK,CHECK-SM63 ; RUN: opt -S -passes='dxil-op-lower' -mtriple=dxil-pc-shadermodel6.6-library %s | FileCheck %s --check-prefixes=CHECK,CHECK-SM66 -; RUN: opt -S -dxil-op-lower -dxil-prepare -mtriple=dxil-pc-shadermodel6.6-library %s | FileCheck %s --check-prefixes=CHECK,CHECK-PREPARE ; CHECK-LABEL: define void @test_legal_lifetime() { ; @@ -16,14 +15,6 @@ ; CHECK-SM66-NEXT: store i32 0, ptr [[GEP]], align 4 ; CHECK-SM66-NEXT: call void @llvm.lifetime.end.p0(i64 4, ptr nonnull [[ACCUM_I_FLAT]]) ; -; CHECK-PREPARE-NEXT: [[ACCUM_I_FLAT:%.*]] = alloca [1 x i32], align 4 -; CHECK-PREPARE-NEXT: [[GEP:%.*]] = getelementptr i32, ptr [[ACCUM_I_FLAT]], i32 0 -; CHECK-PREPARE-NEXT: [[BITCAST:%.*]] = bitcast ptr [[ACCUM_I_FLAT]] to ptr -; CHECK-PREPARE-NEXT: call void @llvm.lifetime.start.p0(i64 4, ptr nonnull [[BITCAST]]) -; CHECK-PREPARE-NEXT: store i32 0, ptr [[GEP]], align 4 -; CHECK-PREPARE-NEXT: [[BITCAST:%.*]] = bitcast ptr [[ACCUM_I_FLAT]] to ptr -; CHECK-PREPARE-NEXT: call void @llvm.lifetime.end.p0(i64 4, ptr nonnull [[BITCAST]]) -; ; CHECK-NEXT: ret void ; define void @test_legal_lifetime() { @@ -35,22 +26,6 @@ define void @test_legal_lifetime() { ret void } -; CHECK-PREPARE-DAG: attributes [[LIFETIME_ATTRS:#.*]] = { nounwind } - -; CHECK-PREPARE-DAG: ; Function Attrs: nounwind -; CHECK-PREPARE-DAG: declare void @llvm.lifetime.start.p0(i64, ptr) [[LIFETIME_ATTRS]] - -; CHECK-PREPARE-DAG: ; Function Attrs: nounwind -; CHECK-PREPARE-DAG: declare void @llvm.lifetime.end.p0(i64, ptr) [[LIFETIME_ATTRS]] - -; Function Attrs: nounwind memory(argmem: readwrite) -declare void @llvm.lifetime.end.p0(i64, ptr) #0 - -; Function Attrs: nounwind memory(argmem: readwrite) -declare void @llvm.lifetime.start.p0(i64, ptr) #0 - -attributes #0 = { nounwind memory(argmem: readwrite) } - ; Set the validator version to 1.6 !dx.valver = !{!0} !0 = !{i32 1, i32 6} diff --git a/llvm/test/CodeGen/DirectX/legalize-load-store-array-alloca.ll b/llvm/test/CodeGen/DirectX/legalize-load-store-array-alloca.ll index b25b3de..c6789ac 100644 --- a/llvm/test/CodeGen/DirectX/legalize-load-store-array-alloca.ll +++ b/llvm/test/CodeGen/DirectX/legalize-load-store-array-alloca.ll @@ -21,3 +21,21 @@ define void @store() { store i32 0, ptr %a, align 4
ret void
}
+
+@g = local_unnamed_addr addrspace(3) global [4 x i32] zeroinitializer, align 4
+define void @load_whole_global () {
+; CHECK-LABEL: define void @load_whole_global
+; CHECK-NEXT: load [4 x i32], ptr addrspace(3) @g, align 4
+; CHECK-NEXT: ret void
+ %l = load [4 x i32], ptr addrspace(3) @g, align 4
+ ret void
+}
+
+define void @load_global_index0 () {
+; CHECK-LABEL: define void @load_global_index0
+; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [4 x i32], ptr addrspace(3) @g, i32 0, i32 0
+; CHECK-NEXT: load i32, ptr addrspace(3) [[GEP]], align 4
+; CHECK-NEXT: ret void
+ %l = load i32, ptr addrspace(3) @g, align 4
+ ret void
+}
diff --git a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll index 27a8925..0c91c53 100644 --- a/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll +++ b/llvm/test/CodeGen/DirectX/llc-vector-load-scalarize.ll @@ -24,7 +24,8 @@ define <4 x i32> @load_array_vec_test() #0 { ; CHECK-LABEL: define <4 x i32> @load_array_vec_test( ; CHECK-SAME: ) #[[ATTR0:[0-9]+]] { -; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) @arrayofVecData.scalarized.1dim, align 4 +; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 0 +; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) [[GEP]], align 4 ; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), align 4 ; CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 2), align 4 ; CHECK-NEXT: [[TMP8:%.*]] = load i32, ptr addrspace(3) getelementptr ([8 x i32], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 3), align 4 @@ -52,7 +53,8 @@ define <4 x i32> @load_array_vec_test() #0 { define <4 x i32> @load_vec_test() #0 { ; CHECK-LABEL: define <4 x i32> @load_vec_test( ; CHECK-SAME: ) #[[ATTR0]] { -; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(3) @vecData.scalarized, align 4 +; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 0 +; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(3) [[GEP]], align 4 ; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 1), align 4 ; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 2), align 4 ; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 3), align 4 @@ -203,7 +205,8 @@ define <4 x i32> @load_static_array_of_vec_from_i8_gep_test(i32 %index) #0 { define <4 x i32> @multid_load_test() #0 { ; CHECK-LABEL: define <4 x i32> @multid_load_test( ; CHECK-SAME: ) #[[ATTR0]] { -; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, align 4 +; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 0 +; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(3) [[GEP]], align 4 ; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 1), align 4 ; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 2), align 4 ; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(3) getelementptr ([36 x i32], ptr addrspace(3) @groupshared2dArrayofVectors.scalarized.1dim, i32 0, i32 3), align 4 diff --git a/llvm/test/CodeGen/DirectX/scalar-store.ll b/llvm/test/CodeGen/DirectX/scalar-store.ll index a124c66..4394235 100644 --- a/llvm/test/CodeGen/DirectX/scalar-store.ll +++ b/llvm/test/CodeGen/DirectX/scalar-store.ll @@ -14,7 +14,8 @@ ; CHECK-LABEL: store_array_vec_test define void @store_array_vec_test () local_unnamed_addr #0 { -; CHECK-NEXT: store float 1.000000e+00, ptr addrspace(3) @arrayofVecData.scalarized.1dim, align 16 +; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 0 +; CHECK-NEXT: store float 1.000000e+00, ptr addrspace(3) [[GEP]], align 16 ; CHECK-NEXT: store float 2.000000e+00, ptr addrspace(3) getelementptr ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 1), align 4 ; CHECK-NEXT: store float 3.000000e+00, ptr addrspace(3) getelementptr ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 2), align 8 ; CHECK-NEXT: store float 2.000000e+00, ptr addrspace(3) getelementptr inbounds ([6 x float], ptr addrspace(3) @arrayofVecData.scalarized.1dim, i32 0, i32 3), align 16 @@ -30,7 +31,8 @@ define void @store_array_vec_test () local_unnamed_addr #0 { ; CHECK-LABEL: store_vec_test define void @store_vec_test(<4 x i32> %inputVec) #0 { ; CHECK-NEXT: [[INPUTVEC_I01:%.*]] = extractelement <4 x i32> %inputVec, i32 0 -; CHECK-NEXT: store i32 [[INPUTVEC_I01]], ptr addrspace(3) @vecData.scalarized, align 4 +; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds nuw [4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 0 +; CHECK-NEXT: store i32 [[INPUTVEC_I01]], ptr addrspace(3) [[GEP]], align 4 ; CHECK-NEXT: [[INPUTVEC_I12:%.*]] = extractelement <4 x i32> %inputVec, i32 1 ; CHECK-NEXT: store i32 [[INPUTVEC_I12]], ptr addrspace(3) getelementptr ([4 x i32], ptr addrspace(3) @vecData.scalarized, i32 0, i32 1), align 4 ; CHECK-NEXT: [[INPUTVEC_I23:%.*]] = extractelement <4 x i32> %inputVec, i32 2 |