[LV] Add coverage for operand-bundles #163417
Open
+235
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-llvm-transforms Author: Ramkumar Ramachandra (artagnon) ChangesFull diff: https://github.com/llvm/llvm-project/pull/163417.diff 1 Files Affected:
diff --git a/llvm/test/Transforms/LoopVectorize/operand-bundles.ll b/llvm/test/Transforms/LoopVectorize/operand-bundles.ll
new file mode 100644
index 0000000000000..262562d625f8d
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/operand-bundles.ll
@@ -0,0 +1,235 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 6
+; RUN: opt -p loop-vectorize -force-vector-width=8 -S %s | FileCheck %s
+
+define void @call_loop_invariant_operand_bundle(ptr %dst, {float, float} %sv) {
+; CHECK-LABEL: define void @call_loop_invariant_operand_bundle(
+; CHECK-SAME: ptr [[DST:%.*]], { float, float } [[SV:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[TMP0:%.*]] = extractvalue { float, float } [[SV]], 0
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x float> poison, float [[TMP0]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x float> [[BROADCAST_SPLATINSERT]], <8 x float> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP1:%.*]] = extractvalue { float, float } [[SV]], 1
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <8 x float> poison, float [[TMP1]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <8 x float> [[BROADCAST_SPLATINSERT1]], <8 x float> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, ptr [[DST]], i32 [[INDEX]]
+; CHECK-NEXT: [[TMP3:%.*]] = call <8 x float> @llvm.pow.v8f32(<8 x float> [[BROADCAST_SPLAT]], <8 x float> [[BROADCAST_SPLAT2]]) [ "deopt"(float 1.000000e+01) ]
+; CHECK-NEXT: store <8 x float> [[TMP3]], ptr [[TMP2]], align 4
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
+; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000
+; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: br label %[[EXIT:.*]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %loop
+
+loop:
+ %iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
+ %a = extractvalue { float, float } %sv, 0
+ %b = extractvalue { float, float } %sv, 1
+ %addr = getelementptr float, ptr %dst, i32 %iv
+ %p = call float @llvm.pow.f32(float %a, float %b) [ "deopt"(float 10.0) ]
+ store float %p, ptr %addr
+ %iv.next = add nsw i32 %iv, 1
+ %cond = icmp ne i32 %iv.next, 1000
+ br i1 %cond, label %loop, label %exit
+
+exit:
+ ret void
+}
+
+define void @call_unknown_operand_bundle(ptr %dst, {float, float} %sv) {
+; CHECK-LABEL: define void @call_unknown_operand_bundle(
+; CHECK-SAME: ptr [[DST:%.*]], { float, float } [[SV:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[TMP0:%.*]] = extractvalue { float, float } [[SV]], 0
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x float> poison, float [[TMP0]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x float> [[BROADCAST_SPLATINSERT]], <8 x float> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP1:%.*]] = extractvalue { float, float } [[SV]], 1
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <8 x float> poison, float [[TMP1]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <8 x float> [[BROADCAST_SPLATINSERT1]], <8 x float> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, ptr [[DST]], i32 [[INDEX]]
+; CHECK-NEXT: [[TMP3:%.*]] = call <8 x float> @llvm.pow.v8f32(<8 x float> [[BROADCAST_SPLAT]], <8 x float> [[BROADCAST_SPLAT2]]) [ "unknown"(ptr null) ]
+; CHECK-NEXT: store <8 x float> [[TMP3]], ptr [[TMP2]], align 4
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
+; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000
+; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: br label %[[EXIT:.*]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %loop
+
+loop:
+ %iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
+ %a = extractvalue { float, float } %sv, 0
+ %b = extractvalue { float, float } %sv, 1
+ %addr = getelementptr float, ptr %dst, i32 %iv
+ %p = call float @llvm.pow.f32(float %a, float %b) [ "unknown"(ptr null) ]
+ store float %p, ptr %addr
+ %iv.next = add nsw i32 %iv, 1
+ %cond = icmp ne i32 %iv.next, 1000
+ br i1 %cond, label %loop, label %exit
+
+exit:
+ ret void
+}
+
+define void @call_cold_operand_bundle(ptr %dst, {float, float} %sv) {
+; CHECK-LABEL: define void @call_cold_operand_bundle(
+; CHECK-SAME: ptr [[DST:%.*]], { float, float } [[SV:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[TMP0:%.*]] = extractvalue { float, float } [[SV]], 0
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x float> poison, float [[TMP0]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x float> [[BROADCAST_SPLATINSERT]], <8 x float> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP1:%.*]] = extractvalue { float, float } [[SV]], 1
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <8 x float> poison, float [[TMP1]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <8 x float> [[BROADCAST_SPLATINSERT1]], <8 x float> poison, <8 x i32> zeroinitializer
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, ptr [[DST]], i32 [[INDEX]]
+; CHECK-NEXT: [[TMP3:%.*]] = call <8 x float> @llvm.pow.v8f32(<8 x float> [[BROADCAST_SPLAT]], <8 x float> [[BROADCAST_SPLAT2]]) [ "cold"() ]
+; CHECK-NEXT: store <8 x float> [[TMP3]], ptr [[TMP2]], align 4
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
+; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000
+; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: br label %[[EXIT:.*]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %loop
+
+loop:
+ %iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
+ %a = extractvalue { float, float } %sv, 0
+ %b = extractvalue { float, float } %sv, 1
+ %addr = getelementptr float, ptr %dst, i32 %iv
+ %p = call float @llvm.pow.f32(float %a, float %b) [ "cold"() ]
+ store float %p, ptr %addr
+ %iv.next = add nsw i32 %iv, 1
+ %cond = icmp ne i32 %iv.next, 1000
+ br i1 %cond, label %loop, label %exit
+
+exit:
+ ret void
+}
+
+define void @assume_loop_variant_operand_bundle(ptr noalias %a, ptr noalias %b) {
+; CHECK-LABEL: define void @assume_loop_variant_operand_bundle(
+; CHECK-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1
+; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2
+; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[INDEX]], 3
+; CHECK-NEXT: [[TMP4:%.*]] = add i64 [[INDEX]], 4
+; CHECK-NEXT: [[TMP5:%.*]] = add i64 [[INDEX]], 5
+; CHECK-NEXT: [[TMP6:%.*]] = add i64 [[INDEX]], 6
+; CHECK-NEXT: [[TMP7:%.*]] = add i64 [[INDEX]], 7
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP0]]
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x float>, ptr [[TMP8]], align 4
+; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP0]]) ]
+; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP1]]) ]
+; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP2]]) ]
+; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP3]]) ]
+; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP4]]) ]
+; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP5]]) ]
+; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP6]]) ]
+; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP7]]) ]
+; CHECK-NEXT: [[TMP9:%.*]] = fadd <8 x float> [[WIDE_LOAD]], splat (float 1.000000e+00)
+; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP0]]
+; CHECK-NEXT: store <8 x float> [[TMP9]], ptr [[TMP10]], align 4
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
+; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1600
+; CHECK-NEXT: br i1 [[TMP11]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: br label %[[EXIT:.*]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %loop
+
+loop:
+ %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+ %arrayidx = getelementptr inbounds float, ptr %b, i64 %iv
+ %0 = load float, ptr %arrayidx, align 4
+ %cmp1 = fcmp ogt float %0, 1.000000e+02
+ tail call void @llvm.assume(i1 true) [ "align"(ptr %a, i64 %iv) ]
+ %add = fadd float %0, 1.000000e+00
+ %arrayidx5 = getelementptr inbounds float, ptr %a, i64 %iv
+ store float %add, ptr %arrayidx5, align 4
+ %iv.next = add nuw nsw i64 %iv, 1
+ %exitcond = icmp eq i64 %iv, 1599
+ br i1 %exitcond, label %exit, label %loop
+
+exit:
+ ret void
+}
+
+define void @assume_cold_operand_bundle(ptr noalias %a, ptr noalias %b) {
+; CHECK-LABEL: define void @assume_cold_operand_bundle(
+; CHECK-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDEX]]
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x float>, ptr [[TMP0]], align 4
+; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "cold"() ]
+; CHECK-NEXT: [[TMP1:%.*]] = fadd <8 x float> [[WIDE_LOAD]], splat (float 1.000000e+00)
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDEX]]
+; CHECK-NEXT: store <8 x float> [[TMP1]], ptr [[TMP2]], align 4
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
+; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1600
+; CHECK-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: br label %[[EXIT:.*]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %loop
+
+loop:
+ %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+ %arrayidx = getelementptr inbounds float, ptr %b, i64 %iv
+ %0 = load float, ptr %arrayidx, align 4
+ %cmp1 = fcmp ogt float %0, 1.000000e+02
+ tail call void @llvm.assume(i1 true) [ "cold"() ]
+ %add = fadd float %0, 1.000000e+00
+ %arrayidx5 = getelementptr inbounds float, ptr %a, i64 %iv
+ store float %add, ptr %arrayidx5, align 4
+ %iv.next = add nuw nsw i64 %iv, 1
+ %exitcond = icmp eq i64 %iv, 1599
+ br i1 %exitcond, label %exit, label %loop
+
+exit:
+ ret void
+}
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.