[llvm] 42cf9c6 - [RISCV] Mark Sub/AddChainWithSubs as legal reduction types (#154753)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Aug 21 06:43:52 PDT 2025
Author: Luke Lau
Date: 2025-08-21T21:43:48+08:00
New Revision: 42cf9c60d77689cbaad5b6a5727c3be0f7f9a605
URL: https://github.com/llvm/llvm-project/commit/42cf9c60d77689cbaad5b6a5727c3be0f7f9a605
DIFF: https://github.com/llvm/llvm-project/commit/42cf9c60d77689cbaad5b6a5727c3be0f7f9a605.diff
LOG: [RISCV] Mark Sub/AddChainWithSubs as legal reduction types (#154753)
We used to vectorize these scalably but after #147026 they were split
out from RecurKind::Add into their own RecurKinds, and we didn't mark
them as supported in isLegalToVectorizeReduction.
This caused the loop vectorizer to drop the scalable VPlan because it
thinks the reductions will be scalarized.
This fixes it by just marking them as supported.
Fixes #154554
Added:
Modified:
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
llvm/test/Transforms/LoopVectorize/RISCV/reductions.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
index b632f25b963f7..3236b2a35c853 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
@@ -372,6 +372,8 @@ class RISCVTTIImpl final : public BasicTTIImplBase<RISCVTTIImpl> {
switch (RdxDesc.getRecurrenceKind()) {
case RecurKind::Add:
+ case RecurKind::Sub:
+ case RecurKind::AddChainWithSubs:
case RecurKind::And:
case RecurKind::Or:
case RecurKind::Xor:
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/reductions.ll b/llvm/test/Transforms/LoopVectorize/RISCV/reductions.ll
index 443951d63397c..f0a42b9214243 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/reductions.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/reductions.ll
@@ -61,6 +61,128 @@ for.end: ; preds = %for.body, %entry
ret i32 %add
}
+define i32 @sub(ptr %a, i64 %n) {
+; CHECK-LABEL: define i32 @sub(
+; CHECK-SAME: ptr [[A:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ insertelement (<vscale x 4 x i32> zeroinitializer, i32 1024, i32 0), %[[VECTOR_PH]] ], [ [[TMP3:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[AVL:%.*]] = phi i64 [ [[N]], %[[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 4, i1 true)
+; CHECK-NEXT: [[TMP0:%.*]] = getelementptr i32, ptr [[A]], i64 [[INDEX]]
+; CHECK-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP0]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP1]])
+; CHECK-NEXT: [[TMP2:%.*]] = sub <vscale x 4 x i32> [[VEC_PHI]], [[VP_OP_LOAD]]
+; CHECK-NEXT: [[TMP3]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP1]])
+; CHECK-NEXT: [[TMP4:%.*]] = zext i32 [[TMP1]] to i64
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP4]], [[INDEX]]
+; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP4]]
+; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
+; CHECK-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[TMP6:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP3]])
+; CHECK-NEXT: br label %[[EXIT:.*]]
+; CHECK: [[SCALAR_PH]]:
+; CHECK-NEXT: br label %[[LOOP:.*]]
+; CHECK: [[LOOP]]:
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[RDX:%.*]] = phi i32 [ 1024, %[[SCALAR_PH]] ], [ [[SUB:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[GEP:%.*]] = getelementptr i32, ptr [[A]], i64 [[IV]]
+; CHECK-NEXT: [[X:%.*]] = load i32, ptr [[GEP]], align 4
+; CHECK-NEXT: [[SUB]] = sub i32 [[RDX]], [[X]]
+; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; CHECK-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
+; CHECK-NEXT: br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: [[SUB_LCSSA:%.*]] = phi i32 [ [[SUB]], %[[LOOP]] ], [ [[TMP6]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: ret i32 [[SUB_LCSSA]]
+;
+entry:
+ br label %loop
+
+loop:
+ %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+ %rdx = phi i32 [ 1024, %entry ], [ %sub, %loop ]
+ %gep = getelementptr i32, ptr %a, i64 %iv
+ %x = load i32, ptr %gep
+ %sub = sub i32 %rdx, %x
+ %iv.next = add i64 %iv, 1
+ %done = icmp eq i64 %iv.next, %n
+ br i1 %done, label %exit, label %loop
+
+exit:
+ ret i32 %sub
+}
+
+define i32 @addsub(ptr %a, ptr %b, i64 %n) {
+; CHECK-LABEL: define i32 @addsub(
+; CHECK-SAME: ptr [[A:%.*]], ptr [[B:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[AVL:%.*]] = phi i64 [ [[N]], %[[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 4, i1 true)
+; CHECK-NEXT: [[TMP0:%.*]] = getelementptr i32, ptr [[A]], i64 [[INDEX]]
+; CHECK-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP0]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP1]])
+; CHECK-NEXT: [[TMP2:%.*]] = add <vscale x 4 x i32> [[VEC_PHI]], [[VP_OP_LOAD]]
+; CHECK-NEXT: [[TMP4:%.*]] = getelementptr i32, ptr [[B]], i64 [[INDEX]]
+; CHECK-NEXT: [[VP_OP_LOAD1:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP4]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP1]])
+; CHECK-NEXT: [[TMP9:%.*]] = sub <vscale x 4 x i32> [[TMP2]], [[VP_OP_LOAD1]]
+; CHECK-NEXT: [[TMP5]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP9]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP1]])
+; CHECK-NEXT: [[TMP6:%.*]] = zext i32 [[TMP1]] to i64
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP6]], [[INDEX]]
+; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP6]]
+; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
+; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[TMP8:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP5]])
+; CHECK-NEXT: br label %[[EXIT:.*]]
+; CHECK: [[SCALAR_PH]]:
+; CHECK-NEXT: br label %[[LOOP:.*]]
+; CHECK: [[LOOP]]:
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[RDX:%.*]] = phi i32 [ 0, %[[SCALAR_PH]] ], [ [[SUB:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[GEP_A:%.*]] = getelementptr i32, ptr [[A]], i64 [[IV]]
+; CHECK-NEXT: [[X:%.*]] = load i32, ptr [[GEP_A]], align 4
+; CHECK-NEXT: [[ADD:%.*]] = add i32 [[RDX]], [[X]]
+; CHECK-NEXT: [[GEP_B:%.*]] = getelementptr i32, ptr [[B]], i64 [[IV]]
+; CHECK-NEXT: [[Y:%.*]] = load i32, ptr [[GEP_B]], align 4
+; CHECK-NEXT: [[SUB]] = sub i32 [[ADD]], [[Y]]
+; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; CHECK-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
+; CHECK-NEXT: br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: [[SUB_LCSSA:%.*]] = phi i32 [ [[SUB]], %[[LOOP]] ], [ [[TMP8]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: ret i32 [[SUB_LCSSA]]
+;
+entry:
+ br label %loop
+
+loop:
+ %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+ %rdx = phi i32 [ 0, %entry ], [ %sub, %loop ]
+ %gep.a = getelementptr i32, ptr %a, i64 %iv
+ %x = load i32, ptr %gep.a
+ %add = add i32 %rdx, %x
+ %gep.b = getelementptr i32, ptr %b, i64 %iv
+ %y = load i32, ptr %gep.b
+ %sub = sub i32 %add, %y
+ %iv.next = add i64 %iv, 1
+ %done = icmp eq i64 %iv.next, %n
+ br i1 %done, label %exit, label %loop
+
+exit:
+ ret i32 %sub
+}
+
+
; OR
define i32 @or(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
@@ -83,7 +205,7 @@ define i32 @or(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP9]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP9]]
; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP11:%.*]] = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> [[TMP8]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -97,7 +219,7 @@ define i32 @or(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[OR]] = or i32 [[TMP10]], [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[OR_LCSSA:%.*]] = phi i32 [ [[OR]], %[[FOR_BODY]] ], [ [[TMP11]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i32 [[OR_LCSSA]]
@@ -141,7 +263,7 @@ define i32 @and(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP9]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP9]]
; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP11:%.*]] = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> [[TMP8]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -155,7 +277,7 @@ define i32 @and(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[AND]] = and i32 [[TMP10]], [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[AND_LCSSA:%.*]] = phi i32 [ [[AND]], %[[FOR_BODY]] ], [ [[TMP11]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i32 [[AND_LCSSA]]
@@ -199,7 +321,7 @@ define i32 @xor(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP9]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP9]]
; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP11:%.*]] = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> [[TMP8]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -213,7 +335,7 @@ define i32 @xor(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[XOR]] = xor i32 [[TMP10]], [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[XOR_LCSSA:%.*]] = phi i32 [ [[XOR]], %[[FOR_BODY]] ], [ [[TMP11]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i32 [[XOR_LCSSA]]
@@ -258,7 +380,7 @@ define i32 @smin(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP12:%.*]] = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -273,7 +395,7 @@ define i32 @smin(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[DOTSROA_SPECULATED]] = select i1 [[CMP_I]], i32 [[TMP11]], i32 [[SUM_010]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[DOTSROA_SPECULATED_LCSSA:%.*]] = phi i32 [ [[DOTSROA_SPECULATED]], %[[FOR_BODY]] ], [ [[TMP12]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i32 [[DOTSROA_SPECULATED_LCSSA]]
@@ -319,7 +441,7 @@ define i32 @umax(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP12:%.*]] = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -334,7 +456,7 @@ define i32 @umax(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[DOTSROA_SPECULATED]] = select i1 [[CMP_I]], i32 [[TMP11]], i32 [[SUM_010]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP18:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[DOTSROA_SPECULATED_LCSSA:%.*]] = phi i32 [ [[DOTSROA_SPECULATED]], %[[FOR_BODY]] ], [ [[TMP12]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i32 [[DOTSROA_SPECULATED_LCSSA]]
@@ -379,7 +501,7 @@ define float @fadd_fast(ptr noalias nocapture readonly %a, i64 %n) {
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP9]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP9]]
; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP19:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP11:%.*]] = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> [[TMP8]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -393,7 +515,7 @@ define float @fadd_fast(ptr noalias nocapture readonly %a, i64 %n) {
; CHECK-NEXT: [[ADD]] = fadd fast float [[TMP10]], [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi float [ [[ADD]], %[[FOR_BODY]] ], [ [[TMP11]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret float [[ADD_LCSSA]]
@@ -435,7 +557,7 @@ define half @fadd_fast_half_zvfh(ptr noalias nocapture readonly %a, i64 %n) "tar
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP9]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP9]]
; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP21:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP11:%.*]] = call fast half @llvm.vector.reduce.fadd.nxv8f16(half 0xH0000, <vscale x 8 x half> [[TMP8]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -449,7 +571,7 @@ define half @fadd_fast_half_zvfh(ptr noalias nocapture readonly %a, i64 %n) "tar
; CHECK-NEXT: [[ADD]] = fadd fast half [[TMP10]], [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP18:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP22:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi half [ [[ADD]], %[[FOR_BODY]] ], [ [[TMP11]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret half [[ADD_LCSSA]]
@@ -493,7 +615,7 @@ define half @fadd_fast_half_zvfhmin(ptr noalias nocapture readonly %a, i64 %n) "
; CHECK-NEXT: [[TMP3]] = fadd fast <16 x half> [[WIDE_LOAD2]], [[VEC_PHI1]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 32
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP19:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP23:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd fast <16 x half> [[TMP3]], [[TMP2]]
; CHECK-NEXT: [[TMP5:%.*]] = call fast half @llvm.vector.reduce.fadd.v16f16(half 0xH0000, <16 x half> [[BIN_RDX]])
@@ -511,7 +633,7 @@ define half @fadd_fast_half_zvfhmin(ptr noalias nocapture readonly %a, i64 %n) "
; CHECK-NEXT: [[ADD]] = fadd fast half [[TMP6]], [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP24:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi half [ [[ADD]], %[[FOR_BODY]] ], [ [[TMP5]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret half [[ADD_LCSSA]]
@@ -555,7 +677,7 @@ define bfloat @fadd_fast_bfloat(ptr noalias nocapture readonly %a, i64 %n) "targ
; CHECK-NEXT: [[TMP3]] = fadd fast <16 x bfloat> [[WIDE_LOAD2]], [[VEC_PHI1]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 32
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP21:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP25:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd fast <16 x bfloat> [[TMP3]], [[TMP2]]
; CHECK-NEXT: [[TMP5:%.*]] = call fast bfloat @llvm.vector.reduce.fadd.v16bf16(bfloat 0xR0000, <16 x bfloat> [[BIN_RDX]])
@@ -573,7 +695,7 @@ define bfloat @fadd_fast_bfloat(ptr noalias nocapture readonly %a, i64 %n) "targ
; CHECK-NEXT: [[ADD]] = fadd fast bfloat [[TMP6]], [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP22:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP26:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi bfloat [ [[ADD]], %[[FOR_BODY]] ], [ [[TMP5]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret bfloat [[ADD_LCSSA]]
@@ -618,7 +740,7 @@ define float @fmin_fast(ptr noalias nocapture readonly %a, i64 %n) #0 {
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP23:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP27:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP12:%.*]] = call float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -633,7 +755,7 @@ define float @fmin_fast(ptr noalias nocapture readonly %a, i64 %n) #0 {
; CHECK-NEXT: [[DOTSROA_SPECULATED]] = select i1 [[CMP_I]], float [[TMP11]], float [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP24:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP28:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[DOTSROA_SPECULATED_LCSSA:%.*]] = phi float [ [[DOTSROA_SPECULATED]], %[[FOR_BODY]] ], [ [[TMP12]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret float [[DOTSROA_SPECULATED_LCSSA]]
@@ -677,7 +799,7 @@ define half @fmin_fast_half_zvfhmin(ptr noalias nocapture readonly %a, i64 %n) #
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP25:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP29:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP12:%.*]] = call half @llvm.vector.reduce.fmin.nxv8f16(<vscale x 8 x half> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -692,7 +814,7 @@ define half @fmin_fast_half_zvfhmin(ptr noalias nocapture readonly %a, i64 %n) #
; CHECK-NEXT: [[DOTSROA_SPECULATED]] = select i1 [[CMP_I]], half [[TMP11]], half [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP26:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP30:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[DOTSROA_SPECULATED_LCSSA:%.*]] = phi half [ [[DOTSROA_SPECULATED]], %[[FOR_BODY]] ], [ [[TMP12]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret half [[DOTSROA_SPECULATED_LCSSA]]
@@ -736,7 +858,7 @@ define bfloat @fmin_fast_bfloat_zvfbfmin(ptr noalias nocapture readonly %a, i64
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP27:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP31:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP12:%.*]] = call bfloat @llvm.vector.reduce.fmin.nxv8bf16(<vscale x 8 x bfloat> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -751,7 +873,7 @@ define bfloat @fmin_fast_bfloat_zvfbfmin(ptr noalias nocapture readonly %a, i64
; CHECK-NEXT: [[DOTSROA_SPECULATED]] = select i1 [[CMP_I]], bfloat [[TMP11]], bfloat [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP28:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP32:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[DOTSROA_SPECULATED_LCSSA:%.*]] = phi bfloat [ [[DOTSROA_SPECULATED]], %[[FOR_BODY]] ], [ [[TMP12]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret bfloat [[DOTSROA_SPECULATED_LCSSA]]
@@ -797,7 +919,7 @@ define float @fmax_fast(ptr noalias nocapture readonly %a, i64 %n) #0 {
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP29:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP33:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP12:%.*]] = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -812,7 +934,7 @@ define float @fmax_fast(ptr noalias nocapture readonly %a, i64 %n) #0 {
; CHECK-NEXT: [[DOTSROA_SPECULATED]] = select i1 [[CMP_I]], float [[TMP11]], float [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP30:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP34:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[DOTSROA_SPECULATED_LCSSA:%.*]] = phi float [ [[DOTSROA_SPECULATED]], %[[FOR_BODY]] ], [ [[TMP12]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret float [[DOTSROA_SPECULATED_LCSSA]]
@@ -856,7 +978,7 @@ define half @fmax_fast_half_zvfhmin(ptr noalias nocapture readonly %a, i64 %n) #
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP31:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP35:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP12:%.*]] = call fast half @llvm.vector.reduce.fmax.nxv8f16(<vscale x 8 x half> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -871,7 +993,7 @@ define half @fmax_fast_half_zvfhmin(ptr noalias nocapture readonly %a, i64 %n) #
; CHECK-NEXT: [[DOTSROA_SPECULATED]] = select i1 [[CMP_I]], half [[TMP11]], half [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP32:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP36:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[DOTSROA_SPECULATED_LCSSA:%.*]] = phi half [ [[DOTSROA_SPECULATED]], %[[FOR_BODY]] ], [ [[TMP12]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret half [[DOTSROA_SPECULATED_LCSSA]]
@@ -915,7 +1037,7 @@ define bfloat @fmax_fast_bfloat_zvfbfmin(ptr noalias nocapture readonly %a, i64
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP33:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP37:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP12:%.*]] = call fast bfloat @llvm.vector.reduce.fmax.nxv8bf16(<vscale x 8 x bfloat> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -930,7 +1052,7 @@ define bfloat @fmax_fast_bfloat_zvfbfmin(ptr noalias nocapture readonly %a, i64
; CHECK-NEXT: [[DOTSROA_SPECULATED]] = select i1 [[CMP_I]], bfloat [[TMP11]], bfloat [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP34:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP38:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[DOTSROA_SPECULATED_LCSSA:%.*]] = phi bfloat [ [[DOTSROA_SPECULATED]], %[[FOR_BODY]] ], [ [[TMP12]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret bfloat [[DOTSROA_SPECULATED_LCSSA]]
@@ -979,7 +1101,7 @@ define i32 @mul(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[TMP3]] = mul <8 x i32> [[WIDE_LOAD2]], [[VEC_PHI1]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP35:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP39:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[BIN_RDX:%.*]] = mul <8 x i32> [[TMP3]], [[TMP2]]
; CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.vector.reduce.mul.v8i32(<8 x i32> [[BIN_RDX]])
@@ -997,7 +1119,7 @@ define i32 @mul(ptr nocapture %a, ptr nocapture readonly %b, i64 %n) {
; CHECK-NEXT: [[MUL]] = mul nsw i32 [[TMP6]], [[SUM_07]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP36:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP40:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[MUL_LCSSA:%.*]] = phi i32 [ [[MUL]], %[[FOR_BODY]] ], [ [[TMP5]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i32 [[MUL_LCSSA]]
@@ -1044,7 +1166,7 @@ define i32 @memory_dependence(ptr noalias nocapture %a, ptr noalias nocapture re
; CHECK-NEXT: [[TMP5]] = mul <8 x i32> [[WIDE_LOAD1]], [[VEC_PHI]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP37:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP41:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.vector.reduce.mul.v8i32(<8 x i32> [[TMP5]])
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
@@ -1067,7 +1189,7 @@ define i32 @memory_dependence(ptr noalias nocapture %a, ptr noalias nocapture re
; CHECK-NEXT: [[MUL]] = mul nsw i32 [[TMP9]], [[SUM]]
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP38:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP42:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[MUL_LCSSA:%.*]] = phi i32 [ [[MUL]], %[[FOR_BODY]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i32 [[MUL_LCSSA]]
@@ -1117,7 +1239,7 @@ define float @fmuladd(ptr %a, ptr %b, i64 %n) {
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP39:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP43:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP16:%.*]] = call reassoc float @llvm.vector.reduce.fadd.nxv4f32(float -0.000000e+00, <vscale x 4 x float> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -1133,7 +1255,7 @@ define float @fmuladd(ptr %a, ptr %b, i64 %n) {
; CHECK-NEXT: [[MULADD]] = tail call reassoc float @llvm.fmuladd.f32(float [[TMP11]], float [[TMP12]], float [[SUM_07]])
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP40:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP44:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[MULADD_LCSSA:%.*]] = phi float [ [[MULADD]], %[[FOR_BODY]] ], [ [[TMP16]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret float [[MULADD_LCSSA]]
@@ -1179,7 +1301,7 @@ define half @fmuladd_f16_zvfh(ptr %a, ptr %b, i64 %n) "target-features"="+zvfh"
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP10]], [[INDEX]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP41:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP45:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP16:%.*]] = call reassoc half @llvm.vector.reduce.fadd.nxv8f16(half 0xH8000, <vscale x 8 x half> [[TMP9]])
; CHECK-NEXT: br label %[[FOR_END:.*]]
@@ -1195,7 +1317,7 @@ define half @fmuladd_f16_zvfh(ptr %a, ptr %b, i64 %n) "target-features"="+zvfh"
; CHECK-NEXT: [[MULADD]] = tail call reassoc half @llvm.fmuladd.f16(half [[TMP11]], half [[TMP12]], half [[SUM_07]])
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP42:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP46:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[MULADD_LCSSA:%.*]] = phi half [ [[MULADD]], %[[FOR_BODY]] ], [ [[TMP16]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret half [[MULADD_LCSSA]]
@@ -1248,7 +1370,7 @@ define half @fmuladd_f16_zvfhmin(ptr %a, ptr %b, i64 %n) "target-features"="+zvf
; CHECK-NEXT: [[TMP5]] = call reassoc <16 x half> @llvm.fmuladd.v16f16(<16 x half> [[WIDE_LOAD2]], <16 x half> [[WIDE_LOAD4]], <16 x half> [[VEC_PHI1]])
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 32
; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP43:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP47:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd reassoc <16 x half> [[TMP5]], [[TMP4]]
; CHECK-NEXT: [[TMP7:%.*]] = call reassoc half @llvm.vector.reduce.fadd.v16f16(half 0xH8000, <16 x half> [[BIN_RDX]])
@@ -1268,7 +1390,7 @@ define half @fmuladd_f16_zvfhmin(ptr %a, ptr %b, i64 %n) "target-features"="+zvf
; CHECK-NEXT: [[MULADD]] = tail call reassoc half @llvm.fmuladd.f16(half [[TMP8]], half [[TMP9]], half [[SUM_07]])
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP44:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP48:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[MULADD_LCSSA:%.*]] = phi half [ [[MULADD]], %[[FOR_BODY]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret half [[MULADD_LCSSA]]
@@ -1318,7 +1440,7 @@ define bfloat @fmuladd_bf16(ptr %a, ptr %b, i64 %n) "target-features"="+zvfbfmin
; CHECK-NEXT: [[TMP5]] = call reassoc <16 x bfloat> @llvm.fmuladd.v16bf16(<16 x bfloat> [[WIDE_LOAD2]], <16 x bfloat> [[WIDE_LOAD4]], <16 x bfloat> [[VEC_PHI1]])
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 32
; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP45:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP49:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd reassoc <16 x bfloat> [[TMP5]], [[TMP4]]
; CHECK-NEXT: [[TMP7:%.*]] = call reassoc bfloat @llvm.vector.reduce.fadd.v16bf16(bfloat 0xR8000, <16 x bfloat> [[BIN_RDX]])
@@ -1338,7 +1460,7 @@ define bfloat @fmuladd_bf16(ptr %a, ptr %b, i64 %n) "target-features"="+zvfbfmin
; CHECK-NEXT: [[MULADD]] = tail call reassoc bfloat @llvm.fmuladd.bf16(bfloat [[TMP8]], bfloat [[TMP9]], bfloat [[SUM_07]])
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP46:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP50:![0-9]+]]
; CHECK: [[FOR_END]]:
; CHECK-NEXT: [[MULADD_LCSSA:%.*]] = phi bfloat [ [[MULADD]], %[[FOR_BODY]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret bfloat [[MULADD_LCSSA]]
More information about the llvm-commits
mailing list