[llvm-branch-commits] [llvm] [LV] Disable epilogue vectorization for FindLastIV if start is poison. (PR #135666)
via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Tue Apr 15 00:29:17 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Florian Hahn (fhahn)
<details>
<summary>Changes</summary>
Back-porting properly freezing of the start value during epilogue
vectorization (https://github.com/llvm/llvm-project/commit/2bdc1a1337692a5743658ba6b680e5d914e684a4) is non-trivial. For the 20.x release, just
disable epilogue vectorization for FindLastIV reductions where the start
value may be poison or undef.
Fixes https://github.com/llvm/llvm-project/issues/126836.
---
Full diff: https://github.com/llvm/llvm-project/pull/135666.diff
3 Files Affected:
- (modified) llvm/lib/Transforms/Vectorize/LoopVectorize.cpp (+10)
- (added) llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll (+166)
- (modified) llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll (+72-11)
``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 7cd395255163a..1baec6d6ca37b 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4626,6 +4626,16 @@ bool LoopVectorizationPlanner::isCandidateForEpilogueVectorization(
return false;
}
+ // Don't vectorize the epilogue, if there are FindLastIV recurrences with a
+ // start value may be undef or poison. Such start values would need freezing.
+ if (any_of(Legal->getReductionVars(), [](const auto &P) {
+ return RecurrenceDescriptor::isFindLastIVRecurrenceKind(
+ P.second.getRecurrenceKind()) &&
+ !isGuaranteedNotToBeUndefOrPoison(
+ P.second.getRecurrenceStartValue());
+ }))
+ return false;
+
// Epilogue vectorization code has not been auditted to ensure it handles
// non-latch exits properly. It may be fine, but it needs auditted and
// tested.
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll
new file mode 100644
index 0000000000000..7355aed6ae65f
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll
@@ -0,0 +1,166 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
+; RUN: opt -passes=loop-vectorize -mtriple=arm64-apple-macosx -S %s | FileCheck %s
+
+define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) {
+; CHECK-LABEL: define i8 @select_icmp_var_start(
+; CHECK-SAME: ptr [[A:%.*]], i8 [[N:%.*]], i8 [[START:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: [[TMP0:%.*]] = add i8 [[N]], -1
+; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP0]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1
+; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i32 [[TMP2]], 32
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP2]], 32
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF]]
+; CHECK-NEXT: [[TMP3:%.*]] = trunc i32 [[N_VEC]] to i8
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_IND:%.*]] = phi <16 x i8> [ <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <16 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP10:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <16 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP11:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[STEP_ADD:%.*]] = add <16 x i8> [[VEC_IND]], splat (i8 16)
+; CHECK-NEXT: [[INDEX4:%.*]] = trunc i32 [[INDEX]] to i8
+; CHECK-NEXT: [[TMP5:%.*]] = add i8 [[INDEX4]], 0
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP5]]
+; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0
+; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 16
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP9]], align 8
+; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <16 x i8>, ptr [[TMP7]], align 8
+; CHECK-NEXT: [[TMP17:%.*]] = icmp eq <16 x i8> [[WIDE_LOAD]], splat (i8 3)
+; CHECK-NEXT: [[TMP23:%.*]] = icmp eq <16 x i8> [[WIDE_LOAD3]], splat (i8 3)
+; CHECK-NEXT: [[TMP10]] = select <16 x i1> [[TMP17]], <16 x i8> [[VEC_IND]], <16 x i8> [[VEC_PHI]]
+; CHECK-NEXT: [[TMP11]] = select <16 x i1> [[TMP23]], <16 x i8> [[STEP_ADD]], <16 x i8> [[VEC_PHI2]]
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 32
+; CHECK-NEXT: [[VEC_IND_NEXT]] = add <16 x i8> [[STEP_ADD]], splat (i8 16)
+; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <16 x i8> @llvm.smax.v16i8(<16 x i8> [[TMP10]], <16 x i8> [[TMP11]])
+; CHECK-NEXT: [[TMP13:%.*]] = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> [[RDX_MINMAX]])
+; CHECK-NEXT: [[RDX_SELECT_CMP12:%.*]] = icmp ne i8 [[TMP13]], -128
+; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP12]], i8 [[TMP13]], i8 [[START]]
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK: [[SCALAR_PH]]:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT: br label %[[LOOP:.*]]
+; CHECK: [[LOOP]]:
+; CHECK-NEXT: [[IV1:%.*]] = phi i8 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV1]]
+; CHECK-NEXT: [[L:%.*]] = load i8, ptr [[GEP1]], align 8
+; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[L]], 3
+; CHECK-NEXT: [[SEL]] = select i1 [[C]], i8 [[IV1]], i8 [[RDX]]
+; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i8 [[IV1]], 1
+; CHECK-NEXT: [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]]
+; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: ret i8 [[SEL_LCSSA]]
+;
+entry:
+ br label %loop
+
+loop:
+ %iv = phi i8 [ 0, %entry ], [ %iv.next, %loop ]
+ %rdx = phi i8 [ %start, %entry ], [ %sel, %loop ]
+ %gep = getelementptr inbounds i8, ptr %a, i8 %iv
+ %l = load i8, ptr %gep, align 8
+ %c = icmp eq i8 %l, 3
+ %sel = select i1 %c, i8 %iv, i8 %rdx
+ %iv.next = add nuw nsw i8 %iv, 1
+ %ec = icmp eq i8 %iv.next, %n
+ br i1 %ec, label %exit, label %loop
+
+exit:
+ ret i8 %sel
+}
+
+define i32 @select_icmp_var_start_iv_trunc(i32 %N, i32 %start) #0 {
+; CHECK-LABEL: define i32 @select_icmp_var_start_iv_trunc(
+; CHECK-SAME: i32 [[N:%.*]], i32 [[START:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: [[N_POS:%.*]] = icmp sgt i32 [[N]], 0
+; CHECK-NEXT: call void @llvm.assume(i1 [[N_POS]])
+; CHECK-NEXT: [[N_EXT:%.*]] = zext i32 [[N]] to i64
+; CHECK-NEXT: [[TMP0:%.*]] = add nuw nsw i64 [[N_EXT]], 1
+; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[TMP0]], 16
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 16
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[START]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP1:%.*]] = icmp eq <4 x i32> [[BROADCAST_SPLAT]], zeroinitializer
+; 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 <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP3:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP6:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[STEP_ADD:%.*]] = add <4 x i32> [[VEC_IND]], splat (i32 4)
+; CHECK-NEXT: [[STEP_ADD_2:%.*]] = add <4 x i32> [[STEP_ADD]], splat (i32 4)
+; CHECK-NEXT: [[STEP_ADD_3:%.*]] = add <4 x i32> [[STEP_ADD_2]], splat (i32 4)
+; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
+; CHECK-NEXT: [[TMP3]] = select i1 [[TMP2]], <4 x i32> [[VEC_IND]], <4 x i32> [[VEC_PHI]]
+; CHECK-NEXT: [[TMP4]] = select i1 [[TMP2]], <4 x i32> [[STEP_ADD]], <4 x i32> [[VEC_PHI2]]
+; CHECK-NEXT: [[TMP5]] = select i1 [[TMP2]], <4 x i32> [[STEP_ADD_2]], <4 x i32> [[VEC_PHI3]]
+; CHECK-NEXT: [[TMP6]] = select i1 [[TMP2]], <4 x i32> [[STEP_ADD_3]], <4 x i32> [[VEC_PHI4]]
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[STEP_ADD_3]], splat (i32 4)
+; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[TMP3]], <4 x i32> [[TMP4]])
+; CHECK-NEXT: [[RDX_MINMAX5:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[RDX_MINMAX]], <4 x i32> [[TMP5]])
+; CHECK-NEXT: [[RDX_MINMAX6:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[RDX_MINMAX5]], <4 x i32> [[TMP6]])
+; CHECK-NEXT: [[TMP16:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[RDX_MINMAX6]])
+; CHECK-NEXT: [[RDX_SELECT_CMP18:%.*]] = icmp ne i32 [[TMP16]], -2147483648
+; CHECK-NEXT: [[RDX_SELECT19:%.*]] = select i1 [[RDX_SELECT_CMP18]], i32 [[TMP16]], i32 [[START]]
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK: [[SCALAR_PH]]:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i32 [ [[RDX_SELECT19]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT: br label %[[LOOP:.*]]
+; CHECK: [[LOOP]]:
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[C:%.*]] = icmp eq i32 [[START]], 0
+; CHECK-NEXT: [[IV_TRUNC:%.*]] = trunc i64 [[IV]] to i32
+; CHECK-NEXT: [[RED_NEXT]] = select i1 [[C]], i32 [[IV_TRUNC]], i32 [[RED]]
+; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], [[N_EXT]]
+; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[RDX_SELECT19]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: ret i32 [[RED_NEXT_LCSSA]]
+;
+entry:
+ %N.pos = icmp sgt i32 %N, 0
+ call void @llvm.assume(i1 %N.pos)
+ %N.ext = zext i32 %N to i64
+ br label %loop
+
+loop:
+ %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+ %red = phi i32 [ %start, %entry ], [ %red.next, %loop ]
+ %c = icmp eq i32 %start, 0
+ %iv.trunc = trunc i64 %iv to i32
+ %red.next = select i1 %c, i32 %iv.trunc, i32 %red
+ %iv.next = add i64 %iv, 1
+ %ec = icmp eq i64 %iv, %N.ext
+ br i1 %ec, label %exit, label %loop
+
+exit:
+ ret i32 %red.next
+}
+
+declare void @llvm.assume(i1 noundef)
+
+attributes #0 = { "target-cpu"="apple-m1" }
diff --git a/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll
index 06f0f05889116..26719f6821673 100644
--- a/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll
+++ b/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
; RUN: opt -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -epilogue-vectorization-force-VF=4 -S < %s | FileCheck %s
define i64 @select_icmp_const(ptr %a, i64 %n) {
@@ -212,13 +212,74 @@ loop:
exit:
ret i64 %sel
}
-;.
-; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
-; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
-; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
-; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META1]], [[META2]]}
-; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META2]], [[META1]]}
-; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META1]], [[META2]]}
-; CHECK: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META2]]}
-; CHECK: [[LOOP7]] = distinct !{[[LOOP7]], [[META2]], [[META1]]}
-;.
+
+define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) {
+; CHECK-LABEL: define i8 @select_icmp_var_start(
+; CHECK-SAME: ptr [[A:%.*]], i8 [[N:%.*]], i8 [[START:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: [[TMP0:%.*]] = add i8 [[N]], -1
+; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP0]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1
+; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i32 [[TMP2]], 4
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[N_MOD_VF2:%.*]] = urem i32 [[TMP2]], 4
+; CHECK-NEXT: [[N_VEC3:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF2]]
+; CHECK-NEXT: [[TMP13:%.*]] = trunc i32 [[N_VEC3]] to i8
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX4:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT11:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_IND5:%.*]] = phi <4 x i8> [ <i8 0, i8 1, i8 2, i8 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT6:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI7:%.*]] = phi <4 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP17:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[OFFSET_IDX:%.*]] = trunc i32 [[INDEX4]] to i8
+; CHECK-NEXT: [[TMP21:%.*]] = add i8 [[OFFSET_IDX]], 0
+; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP21]]
+; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds i8, ptr [[TMP14]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD10:%.*]] = load <4 x i8>, ptr [[TMP15]], align 8
+; CHECK-NEXT: [[TMP16:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD10]], splat (i8 3)
+; CHECK-NEXT: [[TMP17]] = select <4 x i1> [[TMP16]], <4 x i8> [[VEC_IND5]], <4 x i8> [[VEC_PHI7]]
+; CHECK-NEXT: [[INDEX_NEXT11]] = add nuw i32 [[INDEX4]], 4
+; CHECK-NEXT: [[VEC_IND_NEXT6]] = add <4 x i8> [[VEC_IND5]], splat (i8 4)
+; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i32 [[INDEX_NEXT11]], [[N_VEC3]]
+; CHECK-NEXT: br i1 [[TMP18]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[TMP19:%.*]] = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> [[TMP17]])
+; CHECK-NEXT: [[RDX_SELECT_CMP12:%.*]] = icmp ne i8 [[TMP19]], -128
+; CHECK-NEXT: [[RDX_SELECT13:%.*]] = select i1 [[RDX_SELECT_CMP12]], i8 [[TMP19]], i8 [[START]]
+; CHECK-NEXT: [[CMP_N14:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC3]]
+; CHECK-NEXT: br i1 [[CMP_N14]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK: [[SCALAR_PH]]:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP13]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT13]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT: br label %[[LOOP:.*]]
+; CHECK: [[LOOP]]:
+; CHECK-NEXT: [[IV:%.*]] = phi i8 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV]]
+; CHECK-NEXT: [[L:%.*]] = load i8, ptr [[GEP]], align 8
+; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[L]], 3
+; CHECK-NEXT: [[SEL]] = select i1 [[C]], i8 [[IV]], i8 [[RDX]]
+; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i8 [[IV]], 1
+; CHECK-NEXT: [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]]
+; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT13]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: ret i8 [[SEL_LCSSA]]
+;
+entry:
+ br label %loop
+
+loop:
+ %iv = phi i8 [ 0, %entry ], [ %iv.next, %loop ]
+ %rdx = phi i8 [ %start, %entry ], [ %sel, %loop ]
+ %gep = getelementptr inbounds i8, ptr %a, i8 %iv
+ %l = load i8, ptr %gep, align 8
+ %c = icmp eq i8 %l, 3
+ %sel = select i1 %c, i8 %iv, i8 %rdx
+ %iv.next = add nuw nsw i8 %iv, 1
+ %ec = icmp eq i8 %iv.next, %n
+ br i1 %ec, label %exit, label %loop
+
+exit:
+ ret i8 %sel
+}
``````````
</details>
https://github.com/llvm/llvm-project/pull/135666
More information about the llvm-branch-commits
mailing list