[RISCV][TTI] Add test coverage for getPartialReductionCost [nfc]

Adding testing in advance of a change to cost the zvqdotq instructions
such that we emit them from LV.

1 files changed, 250 insertions, 0 deletions

diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/partial-reduce-dot-product.ll b/llvm/test/Transforms/LoopVectorize/RISCV/partial-reduce-dot-product.ll
new file mode 100644
index 0000000..61eec93
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/partial-reduce-dot-product.ll
@@ -0,0 +1,250 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph:" --version 4
+; RUN: opt -passes=loop-vectorize -mattr=+v -S < %s | FileCheck %s --check-prefixes=CHECK,V
+; RUN: opt -passes=loop-vectorize -mattr=+v,+experimental-zvqdotq -S < %s | FileCheck %s --check-prefixes=CHECK,ZVQDOTQ
+
+target triple = "riscv64-none-unknown-elf"
+
+define i32 @vqdot(ptr %a, ptr %b) #0 {
+; CHECK-LABEL: define i32 @vqdot(
+; CHECK-SAME: ptr [[A:%.*]], ptr [[B:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP13:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i8, ptr [[A]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i8, ptr [[TMP6]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i8>, ptr [[TMP7]], align 1
+; CHECK-NEXT:    [[TMP8:%.*]] = sext <vscale x 4 x i8> [[WIDE_LOAD]] to <vscale x 4 x i32>
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr i8, ptr [[B]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i8, ptr [[TMP9]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 4 x i8>, ptr [[TMP10]], align 1
+; CHECK-NEXT:    [[TMP11:%.*]] = sext <vscale x 4 x i8> [[WIDE_LOAD1]] to <vscale x 4 x i32>
+; CHECK-NEXT:    [[TMP12:%.*]] = mul <vscale x 4 x i32> [[TMP11]], [[TMP8]]
+; CHECK-NEXT:    [[TMP13]] = add <vscale x 4 x i32> [[TMP12]], [[VEC_PHI]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[TMP15:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP13]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %accum = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %gep.a = getelementptr i8, ptr %a, i64 %iv
+  %load.a = load i8, ptr %gep.a, align 1
+  %ext.a = sext i8 %load.a to i32
+  %gep.b = getelementptr i8, ptr %b, i64 %iv
+  %load.b = load i8, ptr %gep.b, align 1
+  %ext.b = sext i8 %load.b to i32
+  %mul = mul i32 %ext.b, %ext.a
+  %add = add i32 %mul, %accum
+  %iv.next = add i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, 1024
+  br i1 %exitcond.not, label %for.exit, label %for.body
+
+for.exit:                        ; preds = %for.body
+  ret i32 %add
+}
+
+
+define i32 @vqdotu(ptr %a, ptr %b) #0 {
+; CHECK-LABEL: define i32 @vqdotu(
+; CHECK-SAME: ptr [[A:%.*]], ptr [[B:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP13:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i8, ptr [[A]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i8, ptr [[TMP6]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i8>, ptr [[TMP7]], align 1
+; CHECK-NEXT:    [[TMP8:%.*]] = zext <vscale x 4 x i8> [[WIDE_LOAD]] to <vscale x 4 x i32>
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr i8, ptr [[B]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i8, ptr [[TMP9]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 4 x i8>, ptr [[TMP10]], align 1
+; CHECK-NEXT:    [[TMP11:%.*]] = zext <vscale x 4 x i8> [[WIDE_LOAD1]] to <vscale x 4 x i32>
+; CHECK-NEXT:    [[TMP12:%.*]] = mul <vscale x 4 x i32> [[TMP11]], [[TMP8]]
+; CHECK-NEXT:    [[TMP13]] = add <vscale x 4 x i32> [[TMP12]], [[VEC_PHI]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[TMP15:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP13]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %accum = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %gep.a = getelementptr i8, ptr %a, i64 %iv
+  %load.a = load i8, ptr %gep.a, align 1
+  %ext.a = zext i8 %load.a to i32
+  %gep.b = getelementptr i8, ptr %b, i64 %iv
+  %load.b = load i8, ptr %gep.b, align 1
+  %ext.b = zext i8 %load.b to i32
+  %mul = mul i32 %ext.b, %ext.a
+  %add = add i32 %mul, %accum
+  %iv.next = add i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, 1024
+  br i1 %exitcond.not, label %for.exit, label %for.body
+
+for.exit:                        ; preds = %for.body
+  ret i32 %add
+}
+
+
+define i32 @vqdotsu(ptr %a, ptr %b) #0 {
+; CHECK-LABEL: define i32 @vqdotsu(
+; CHECK-SAME: ptr [[A:%.*]], ptr [[B:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP13:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i8, ptr [[A]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i8, ptr [[TMP6]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i8>, ptr [[TMP7]], align 1
+; CHECK-NEXT:    [[TMP8:%.*]] = zext <vscale x 4 x i8> [[WIDE_LOAD]] to <vscale x 4 x i32>
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr i8, ptr [[B]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i8, ptr [[TMP9]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 4 x i8>, ptr [[TMP10]], align 1
+; CHECK-NEXT:    [[TMP11:%.*]] = sext <vscale x 4 x i8> [[WIDE_LOAD1]] to <vscale x 4 x i32>
+; CHECK-NEXT:    [[TMP12:%.*]] = mul <vscale x 4 x i32> [[TMP11]], [[TMP8]]
+; CHECK-NEXT:    [[TMP13]] = add <vscale x 4 x i32> [[TMP12]], [[VEC_PHI]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[TMP15:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP13]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %accum = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %gep.a = getelementptr i8, ptr %a, i64 %iv
+  %load.a = load i8, ptr %gep.a, align 1
+  %ext.a = zext i8 %load.a to i32
+  %gep.b = getelementptr i8, ptr %b, i64 %iv
+  %load.b = load i8, ptr %gep.b, align 1
+  %ext.b = sext i8 %load.b to i32
+  %mul = mul i32 %ext.b, %ext.a
+  %add = add i32 %mul, %accum
+  %iv.next = add i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, 1024
+  br i1 %exitcond.not, label %for.exit, label %for.body
+
+for.exit:                        ; preds = %for.body
+  ret i32 %add
+}
+
+define i32 @vqdotsu2(ptr %a, ptr %b) #0 {
+; CHECK-LABEL: define i32 @vqdotsu2(
+; CHECK-SAME: ptr [[A:%.*]], ptr [[B:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP13:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i8, ptr [[A]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i8, ptr [[TMP6]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i8>, ptr [[TMP7]], align 1
+; CHECK-NEXT:    [[TMP8:%.*]] = sext <vscale x 4 x i8> [[WIDE_LOAD]] to <vscale x 4 x i32>
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr i8, ptr [[B]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i8, ptr [[TMP9]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 4 x i8>, ptr [[TMP10]], align 1
+; CHECK-NEXT:    [[TMP11:%.*]] = zext <vscale x 4 x i8> [[WIDE_LOAD1]] to <vscale x 4 x i32>
+; CHECK-NEXT:    [[TMP12:%.*]] = mul <vscale x 4 x i32> [[TMP11]], [[TMP8]]
+; CHECK-NEXT:    [[TMP13]] = add <vscale x 4 x i32> [[TMP12]], [[VEC_PHI]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[TMP15:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP13]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %accum = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %gep.a = getelementptr i8, ptr %a, i64 %iv
+  %load.a = load i8, ptr %gep.a, align 1
+  %ext.a = sext i8 %load.a to i32
+  %gep.b = getelementptr i8, ptr %b, i64 %iv
+  %load.b = load i8, ptr %gep.b, align 1
+  %ext.b = zext i8 %load.b to i32
+  %mul = mul i32 %ext.b, %ext.a
+  %add = add i32 %mul, %accum
+  %iv.next = add i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, 1024
+  br i1 %exitcond.not, label %for.exit, label %for.body
+
+for.exit:                        ; preds = %for.body
+  ret i32 %add
+}
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; V: {{.*}}
+; ZVQDOTQ: {{.*}}