[llvm] [LV] add test for low TC under ARM MVE (PR #93181)

via llvm-commits llvm-commits at lists.llvm.org
Thu May 23 05:17:15 PDT 2024


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-transforms

Author: Ramkumar Ramachandra (artagnon)

<details>
<summary>Changes</summary>

Normally, by rule of thumb, keeping the number of instructions the same, a lower VF is cheaper than a higher one on most targets. ARM MVE is a strange target in that 128-bit vectors are cheaper than smaller vectors. As preparatory work for optimizing LoopVectorize for low TCs either requiring tail-folding or scalar-epilogue, add a test for low TCs under the ARM MVE target.

---

Patch is 31.87 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/93181.diff


2 Files Affected:

- (added) llvm/test/Transforms/LoopVectorize/ARM/low-trip-count.ll (+272) 
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll (+13-152) 


``````````diff
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/low-trip-count.ll b/llvm/test/Transforms/LoopVectorize/ARM/low-trip-count.ll
new file mode 100644
index 0000000000000..d59dad2a82bd2
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/ARM/low-trip-count.ll
@@ -0,0 +1,272 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes=loop-vectorize,simplifycfg -mtriple=thumbv8.1m -mattr=+mve -S < %s | FileCheck %s
+
+define void @trip1_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
+; CHECK-LABEL: @trip1_i8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[I_08]]
+; CHECK-NEXT:    [[TMP0:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP0]], 1
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[I_08]]
+; CHECK-NEXT:    [[TMP1:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP1]]
+; CHECK-NEXT:    store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 1
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
+  %0 = load i8, ptr %arrayidx, align 1
+  %mul = shl i8 %0, 1
+  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
+  %1 = load i8, ptr %arrayidx1, align 1
+  %add = add i8 %mul, %1
+  store i8 %add, ptr %arrayidx1, align 1
+  %inc = add nuw nsw i64 %i.08, 1
+  %exitcond.not = icmp eq i64 %inc, 1
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @trip3_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
+; CHECK-LABEL: @trip3_i8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 0, 0
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[TMP0]], i64 3)
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0(ptr [[TMP2]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i8> poison)
+; CHECK-NEXT:    [[TMP3:%.*]] = shl <4 x i8> [[WIDE_MASKED_LOAD]], <i8 1, i8 1, i8 1, i8 1>
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0(ptr [[TMP5]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i8> poison)
+; CHECK-NEXT:    [[TMP6:%.*]] = add <4 x i8> [[TMP3]], [[WIDE_MASKED_LOAD1]]
+; CHECK-NEXT:    call void @llvm.masked.store.v4i8.p0(<4 x i8> [[TMP6]], ptr [[TMP5]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT:    [[INDEX_NEXT:%.*]] = add i64 0, 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
+  %0 = load i8, ptr %arrayidx, align 1
+  %mul = shl i8 %0, 1
+  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
+  %1 = load i8, ptr %arrayidx1, align 1
+  %add = add i8 %mul, %1
+  store i8 %add, ptr %arrayidx1, align 1
+  %inc = add nuw nsw i64 %i.08, 1
+  %exitcond.not = icmp eq i64 %inc, 3
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @trip5_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
+; CHECK-LABEL: @trip5_i8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 0, 0
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 [[TMP0]], i64 5)
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr [[TMP2]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> poison)
+; CHECK-NEXT:    [[TMP3:%.*]] = shl <8 x i8> [[WIDE_MASKED_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr [[TMP5]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> poison)
+; CHECK-NEXT:    [[TMP6:%.*]] = add <8 x i8> [[TMP3]], [[WIDE_MASKED_LOAD1]]
+; CHECK-NEXT:    call void @llvm.masked.store.v8i8.p0(<8 x i8> [[TMP6]], ptr [[TMP5]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT:    [[INDEX_NEXT:%.*]] = add i64 0, 8
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
+  %0 = load i8, ptr %arrayidx, align 1
+  %mul = shl i8 %0, 1
+  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
+  %1 = load i8, ptr %arrayidx1, align 1
+  %add = add i8 %mul, %1
+  store i8 %add, ptr %arrayidx1, align 1
+  %inc = add nuw nsw i64 %i.08, 1
+  %exitcond.not = icmp eq i64 %inc, 5
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @trip8_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
+; CHECK-LABEL: @trip8_i8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 0, 0
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x i8>, ptr [[TMP2]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = shl <8 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <8 x i8>, ptr [[TMP5]], align 1
+; CHECK-NEXT:    [[TMP6:%.*]] = add <8 x i8> [[TMP3]], [[WIDE_LOAD1]]
+; CHECK-NEXT:    store <8 x i8> [[TMP6]], ptr [[TMP5]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT:%.*]] = add nuw i64 0, 8
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
+  %0 = load i8, ptr %arrayidx, align 1
+  %mul = shl i8 %0, 1
+  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
+  %1 = load i8, ptr %arrayidx1, align 1
+  %add = add i8 %mul, %1
+  store i8 %add, ptr %arrayidx1, align 1
+  %inc = add nuw nsw i64 %i.08, 1
+  %exitcond.not = icmp eq i64 %inc, 8
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @trip16_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
+; CHECK-LABEL: @trip16_i8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 0, 0
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP2]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = shl <16 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <16 x i8>, ptr [[TMP5]], align 1
+; CHECK-NEXT:    [[TMP6:%.*]] = add <16 x i8> [[TMP3]], [[WIDE_LOAD1]]
+; CHECK-NEXT:    store <16 x i8> [[TMP6]], ptr [[TMP5]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT:%.*]] = add nuw i64 0, 16
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
+  %0 = load i8, ptr %arrayidx, align 1
+  %mul = shl i8 %0, 1
+  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
+  %1 = load i8, ptr %arrayidx1, align 1
+  %add = add i8 %mul, %1
+  store i8 %add, ptr %arrayidx1, align 1
+  %inc = add nuw nsw i64 %i.08, 1
+  %exitcond.not = icmp eq i64 %inc, 16
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+define void @trip32_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
+; CHECK-LABEL: @trip32_i8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP2]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = shl <16 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <16 x i8>, ptr [[TMP5]], align 1
+; CHECK-NEXT:    [[TMP6:%.*]] = add <16 x i8> [[TMP3]], [[WIDE_LOAD1]]
+; CHECK-NEXT:    store <16 x i8> [[TMP6]], ptr [[TMP5]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 32
+; CHECK-NEXT:    br i1 [[TMP7]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
+  %0 = load i8, ptr %arrayidx, align 1
+  %mul = shl i8 %0, 1
+  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
+  %1 = load i8, ptr %arrayidx1, align 1
+  %add = add i8 %mul, %1
+  store i8 %add, ptr %arrayidx1, align 1
+  %inc = add nuw nsw i64 %i.08, 1
+  %exitcond.not = icmp eq i64 %inc, 32
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @trip24_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
+; CHECK-LABEL: @trip24_i8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x i8>, ptr [[TMP2]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = shl <8 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <8 x i8>, ptr [[TMP5]], align 1
+; CHECK-NEXT:    [[TMP6:%.*]] = add <8 x i8> [[TMP3]], [[WIDE_LOAD1]]
+; CHECK-NEXT:    store <8 x i8> [[TMP6]], ptr [[TMP5]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
+; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 24
+; CHECK-NEXT:    br i1 [[TMP7]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
+  %0 = load i8, ptr %arrayidx, align 1
+  %mul = shl i8 %0, 1
+  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
+  %1 = load i8, ptr %arrayidx1, align 1
+  %add = add i8 %mul, %1
+  store i8 %add, ptr %arrayidx1, align 1
+  %inc = add nuw nsw i64 %i.08, 1
+  %exitcond.not = icmp eq i64 %inc, 24
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
index 7ccbc98d26567..2e631348ea992 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -passes=loop-vectorize -riscv-v-vector-bits-min=128 -scalable-vectorization=on -force-target-instruction-cost=1 -S < %s | FileCheck %s
+; RUN: opt -passes=loop-vectorize,simplifycfg -riscv-v-vector-bits-min=128 -scalable-vectorization=on -force-target-instruction-cost=1 -S < %s | FileCheck %s
 
 target triple = "riscv64"
 
@@ -45,8 +45,6 @@ for.end:                                          ; preds = %for.body
 define void @trip3_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
 ; CHECK-LABEL: @trip3_i8(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 16
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
@@ -57,10 +55,7 @@ define void @trip3_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 16
-; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
-; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP7:%.*]] = add i64 0, 0
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 [[TMP7]], i64 3)
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP7]]
 ; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0
@@ -71,26 +66,7 @@ define void @trip3_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
 ; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0(ptr [[TMP12]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i8> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 16 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv16i8.p0(<vscale x 16 x i8> [[TMP13]], ptr [[TMP12]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
-; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
-; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
-; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
-; CHECK:       for.body:
-; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[SRC]], i64 [[I_08]]
-; CHECK-NEXT:    [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
-; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP14]], 1
-; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST]], i64 [[I_08]]
-; CHECK-NEXT:    [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
-; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP15]]
-; CHECK-NEXT:    store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
-; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
-; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 3
-; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
-; CHECK:       for.end:
+; CHECK-NEXT:    [[INDEX_NEXT:%.*]] = add i64 0, [[TMP6]]
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -116,8 +92,6 @@ for.end:                                          ; preds = %for.body
 define void @trip5_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
 ; CHECK-LABEL: @trip5_i8(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 16
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
@@ -128,10 +102,7 @@ define void @trip5_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 16
-; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
-; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP7:%.*]] = add i64 0, 0
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 [[TMP7]], i64 5)
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP7]]
 ; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0
@@ -142,26 +113,7 @@ define void @trip5_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
 ; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0(ptr [[TMP12]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i8> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 16 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv16i8.p0(<vscale x 16 x i8> [[TMP13]], ptr [[TMP12]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
-; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
-; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
-; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    br...
[truncated]

``````````

</details>


https://github.com/llvm/llvm-project/pull/93181


More information about the llvm-commits mailing list