[llvm] [msan] Handle AVX512 vector down convert (non-mem) intrinsics (PR #147606)
Thurston Dang via llvm-commits
llvm-commits at lists.llvm.org
Tue Jul 8 15:53:25 PDT 2025
https://github.com/thurstond updated https://github.com/llvm/llvm-project/pull/147606
>From 047a1b1d8f22a0b4c2d0b142747eda645ae8cfb5 Mon Sep 17 00:00:00 2001
From: Thurston Dang <thurston at google.com>
Date: Tue, 8 Jul 2025 01:54:58 +0000
Subject: [PATCH 1/6] [msan] Handle AVX512 vector down convert (non-mem)
intrinsics
This handles llvm.x86.avx512.mask.pmov{,s,us}.*.512 using
handleIntrinsicByApplyingToShadow where possible, otherwise using a
customized slow-path handler, "handleAVX512VectorDownConvert".
Note that shadow propagation of pmov{s,us} (signed/unsigned saturation) are approximated using
truncation. Future work could extend handleAVX512VectorDownConvert to
use GetMinMaxUnsigned() to handle saturation precisely.
---
.../Instrumentation/MemorySanitizer.cpp | 140 ++++
.../MemorySanitizer/X86/avx512-intrinsics.ll | 725 ++++++------------
.../X86/avx512bw-intrinsics.ll | 104 +--
3 files changed, 410 insertions(+), 559 deletions(-)
diff --git a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
index 36fb7d11b488a..83a419eafc8ec 100644
--- a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
@@ -4592,6 +4592,86 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
ConstantInt::get(IRB.getInt32Ty(), 0));
}
+ // Handle llvm.x86.avx512.mask.pmov{,s,us}.*.512
+ //
+ // e.g., call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512
+ // (<8 x i64>, <16 x i8>, i8)
+ // A WriteThru Mask
+ //
+ // call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512
+ // (<16 x i32>, <16 x i8>, i16)
+ //
+ // Dst[i] = Mask[i] ? truncate_or_saturate(A[i]) : WriteThru[i]
+ // Dst_shadow[i] = Mask[i] ? truncate(A_shadow[i]) : WriteThru_shadow[i]
+ //
+ // If Dst has more elements than A, the excess elements are zeroed (and the
+ // corresponding shadow is initialized).
+ //
+ // Note: for PMOV (truncation), handleIntrinsicByApplyingToShadow is precise
+ // and is much faster than this handler.
+ void handleAVX512VectorDownConvert(IntrinsicInst &I) {
+ IRBuilder<> IRB(&I);
+
+ assert(I.arg_size() == 3);
+ Value *A = I.getOperand(0);
+ Value *WriteThrough = I.getOperand(1);
+ Value *Mask = I.getOperand(2);
+
+ assert(isa<FixedVectorType>(A->getType()));
+ assert(A->getType()->isIntOrIntVectorTy());
+
+ assert(isa<FixedVectorType>(WriteThrough->getType()));
+ assert(WriteThrough->getType()->isIntOrIntVectorTy());
+
+ unsigned ANumElements =
+ cast<FixedVectorType>(A->getType())->getNumElements();
+ unsigned OutputNumElements =
+ cast<FixedVectorType>(WriteThrough->getType())->getNumElements();
+ assert(ANumElements == OutputNumElements ||
+ ANumElements * 2 == OutputNumElements);
+
+ assert(Mask->getType()->isIntegerTy());
+ assert(Mask->getType()->getScalarSizeInBits() == ANumElements);
+
+ assert(I.getType() == WriteThrough->getType());
+
+ // Widen the mask, if necessary, to have one bit per element of the output
+ // vector.
+ // We want the extra bits to have '1's, so that the CreateSelect will
+ // select the values from AShadow instead of WriteThroughShadow ("maskless"
+ // versions of the intrinsics are sometimes implemented using an all-1's
+ // mask and an undefined value for WriteThroughShadow). We accomplish this
+ // by using bitwise NOT before and after the ZExt.
+ if (ANumElements != OutputNumElements) {
+ Mask = IRB.CreateNot(Mask);
+ Mask = IRB.CreateZExt(Mask, Type::getIntNTy(*MS.C, OutputNumElements), "_ms_widen_mask");
+ Mask = IRB.CreateNot(Mask);
+ }
+ Mask = IRB.CreateBitCast(
+ Mask, FixedVectorType::get(IRB.getInt1Ty(), OutputNumElements));
+
+ Value *AShadow = getShadow(A);
+
+ // The return type might have more elements than the input.
+ // Temporarily shrink the return type's number of elements.
+ VectorType *ShadowType = maybeShrinkVectorShadowType(A, I);
+
+ // PMOV truncates; PMOVS/PMOVUS uses signed/unsigned saturation.
+ // This handler treats them all as truncation.
+ //
+ // TODO: use GetMinMaxUnsigned() to handle saturation precisely.
+ AShadow = IRB.CreateTrunc(AShadow, ShadowType, "_ms_trunc_shadow");
+
+ AShadow = maybeExtendVectorShadowWithZeros(AShadow, I);
+
+ Value *WriteThroughShadow = getShadow(WriteThrough);
+
+ Value *Shadow = IRB.CreateSelect(Mask, AShadow, WriteThroughShadow);
+
+ setShadow(&I, Shadow);
+ setOriginForNaryOp(I);
+ }
+
// For sh.* compiler intrinsics:
// llvm.x86.avx512fp16.mask.{add/sub/mul/div/max/min}.sh.round
// (<8 x half>, <8 x half>, <8 x half>, i8, i32)
@@ -5412,6 +5492,66 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
break;
}
+ // AVX512 PMOV: Packed MOV, with truncation
+ // Precisely handled by applying the same intrinsic to the shadow
+ case Intrinsic::x86_avx512_mask_pmov_dw_512:
+ case Intrinsic::x86_avx512_mask_pmov_db_512:
+ case Intrinsic::x86_avx512_mask_pmov_qb_512:
+ case Intrinsic::x86_avx512_mask_pmov_qw_512: {
+ // Intrinsic::x86_avx512_mask_pmov_{qd,wb}_512 were removed in
+ // f608dc1f5775ee880e8ea30e2d06ab5a4a935c22
+ handleIntrinsicByApplyingToShadow(I, I.getIntrinsicID(),
+ /*trailingVerbatimArgs=*/1);
+ break;
+ }
+
+ // AVX512 PMVOV{S,US}: Packed MOV, with signed/unsigned saturation
+ // Approximately handled using the corresponding truncation intrinsic
+ // TODO: improve handleAVX512VectorDownConvert to precisely model saturation
+ case Intrinsic::x86_avx512_mask_pmovs_dw_512:
+ case Intrinsic::x86_avx512_mask_pmovus_dw_512: {
+ handleIntrinsicByApplyingToShadow(I,
+ Intrinsic::x86_avx512_mask_pmov_dw_512,
+ /* trailingVerbatimArgs=*/1);
+ break;
+ }
+
+ case Intrinsic::x86_avx512_mask_pmovs_db_512:
+ case Intrinsic::x86_avx512_mask_pmovus_db_512: {
+ handleIntrinsicByApplyingToShadow(I,
+ Intrinsic::x86_avx512_mask_pmov_db_512,
+ /* trailingVerbatimArgs=*/1);
+ break;
+ }
+
+ case Intrinsic::x86_avx512_mask_pmovs_qb_512:
+ case Intrinsic::x86_avx512_mask_pmovus_qb_512: {
+ handleIntrinsicByApplyingToShadow(I,
+ Intrinsic::x86_avx512_mask_pmov_qb_512,
+ /* trailingVerbatimArgs=*/1);
+ break;
+ }
+
+ case Intrinsic::x86_avx512_mask_pmovs_qw_512:
+ case Intrinsic::x86_avx512_mask_pmovus_qw_512: {
+ handleIntrinsicByApplyingToShadow(I,
+ Intrinsic::x86_avx512_mask_pmov_qw_512,
+ /* trailingVerbatimArgs=*/1);
+ break;
+ }
+
+ case Intrinsic::x86_avx512_mask_pmovs_qd_512:
+ case Intrinsic::x86_avx512_mask_pmovus_qd_512:
+ case Intrinsic::x86_avx512_mask_pmovs_wb_512:
+ case Intrinsic::x86_avx512_mask_pmovus_wb_512: {
+ // Since Intrinsic::x86_avx512_mask_pmov_{qd,wb}_512 do not exist, we
+ // cannot use handleIntrinsicByApplyingToShadow. Instead, we call the
+ // slow-path handler.
+ handleAVX512VectorDownConvert(I);
+ break;
+ }
+
+ // AVX512 FP16 Arithmetic
case Intrinsic::x86_avx512fp16_mask_add_sh_round:
case Intrinsic::x86_avx512fp16_mask_sub_sh_round:
case Intrinsic::x86_avx512fp16_mask_mul_sh_round:
diff --git a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
index d9ac1b43924bf..a8d32ce5b2719 100644
--- a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
+++ b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
@@ -2,6 +2,47 @@
; RUN: opt %s -S -mattr=+avx512f -passes=msan 2>&1 | FileCheck %s
;
; Forked from llvm/test/CodeGen/X86/avx512-intrinsics.ll
+;
+; Strictly handled:
+; - llvm.x86.avx512.add.ps.512
+; - llvm.x86.avx512.cvtsi2ss32, llvm.x86.avx512.cvttsd2si, llvm.x86.avx512.cvttss2si
+; - llvm.x86.avx512.div.ps.512
+; - llvm.x86.avx512.mask.add.sd.round, llvm.x86.avx512.mask.add.ss.round
+; - llvm.x86.avx512.mask.cmp.pd.512, llvm.x86.avx512.mask.cmp.ps.512, llvm.x86.avx512.mask.cmp.sd, llvm.x86.avx512.mask.cmp.ss
+; - llvm.x86.avx512.mask.compress.v16f32, llvm.x86.avx512.mask.compress.v16i32llvm.x86.avx512.mask.compress.v8f64, llvm.x86.avx512.mask.compress.v8i64
+; - llvm.x86.avx512.mask.cvtpd2dq.512, llvm.x86.avx512.mask.cvtpd2ps.512, llvm.x86.avx512.mask.cvtpd2udq.512, llvm.x86.avx512.mask.cvtps2pd.512, llvm.x86.avx512.mask.cvtps2udq.512
+; - llvm.x86.avx512.mask.cvtsd2ss.round, llvm.x86.avx512.mask.cvtss2sd.round
+; - llvm.x86.avx512.mask.cvttpd2dq.512, llvm.x86.avx512.mask.cvttpd2udq.512, llvm.x86.avx512.mask.cvttps2dq.512, llvm.x86.avx512.mask.cvttps2udq.512
+; - llvm.x86.avx512.mask.expand.v16f32, llvm.x86.avx512.mask.expand.v16i32, llvm.x86.avx512.mask.expand.v8f64, llvm.x86.avx512.mask.expand.v8i64
+; - llvm.x86.avx512.mask.fixupimm.pd.512, llvm.x86.avx512.mask.fixupimm.ps.512, llvm.x86.avx512.mask.fixupimm.sd, llvm.x86.avx512.mask.fixupimm.ss
+; - llvm.x86.avx512.mask.getexp.pd.512, llvm.x86.avx512.mask.getexp.ps.512, llvm.x86.avx512.mask.getexp.sd, llvm.x86.avx512.mask.getexp.ss
+; - llvm.x86.avx512.mask.getmant.pd.512, llvm.x86.avx512.mask.getmant.ps.512, llvm.x86.avx512.mask.getmant.sd, llvm.x86.avx512.mask.getmant.ss
+; - llvm.x86.avx512.mask.max.sd.round, llvm.x86.avx512.mask.max.ss.round
+; - llvm.x86.avx512.mask.pmov.db.mem.512, llvm.x86.avx512.mask.pmov.dw.mem.512, llvm.x86.avx512.mask.pmov.qb.mem.512, llvm.x86.avx512.mask.pmov.qd.mem.512llvm.x86.avx512.mask.pmov.qw.mem.512
+; - llvm.x86.avx512.mask.pmovs.db.mem.512, llvm.x86.avx512.mask.pmovs.dw.mem.512, llvm.x86.avx512.mask.pmovs.qb.mem.512, llvm.x86.avx512.mask.pmovs.qd.mem.512, llvm.x86.avx512.mask.pmovs.qw.mem.512
+; - llvm.x86.avx512.mask.pmovus.db.mem.512, llvm.x86.avx512.mask.pmovus.dw.mem.512, llvm.x86.avx512.mask.pmovus.qb.mem.512, llvm.x86.avx512.mask.pmovus.qd.mem.512, llvm.x86.avx512.mask.pmovus.qw.mem.512
+; - llvm.x86.avx512.mask.rndscale.pd.512, llvm.x86.avx512.mask.rndscale.ps.512, llvm.x86.avx512.mask.rndscale.sd, llvm.x86.avx512.mask.rndscale.ss
+; - llvm.x86.avx512.mask.scalef.pd.512, llvm.x86.avx512.mask.scalef.ps.512
+; - llvm.x86.avx512.mask.sqrt.sd, llvm.x86.avx512.mask.sqrt.ss
+; - llvm.x86.avx512.mask.vcvtps2ph.512
+; - llvm.x86.avx512.maskz.fixupimm.pd.512, llvm.x86.avx512.maskz.fixupimm.ps.512, llvm.x86.avx512.maskz.fixupimm.sd, llvm.x86.avx512.maskz.fixupimm.ss
+; - llvm.x86.avx512.mul.pd.512, llvm.x86.avx512.mul.ps.512
+; - llvm.x86.avx512.permvar.df.512, llvm.x86.avx512.permvar.sf.512
+; - llvm.x86.avx512.pternlog.d.512, llvm.x86.avx512.pternlog.q.512
+; - llvm.x86.avx512.rcp14.pd.512, llvm.x86.avx512.rcp14.ps.512
+; - llvm.x86.avx512.rsqrt14.ps.512
+; - llvm.x86.avx512.sitofp.round.v16f32.v16i32
+; - llvm.x86.avx512.sqrt.pd.512, llvm.x86.avx512.sqrt.ps.512
+; - llvm.x86.avx512.sub.ps.512
+; - llvm.x86.avx512.uitofp.round.v16f32.v16i32
+; - llvm.x86.avx512.vcomi.sd, llvm.x86.avx512.vcomi.ss
+; - llvm.x86.avx512.vcvtsd2si32, llvm.x86.avx512.vcvtss2si32
+; - llvm.x86.avx512.vfmadd.f32, llvm.x86.avx512.vfmadd.f64
+;
+; Heuristically handled:
+; - llvm.fma.f32, llvm.fma.f64
+; - llvm.sqrt.v16f32, llvm.sqrt.v8f64
+; - llvm.x86.avx512.permvar.di.512, llvm.x86.avx512.permvar.si.512
target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@@ -6565,43 +6606,24 @@ define <16 x i8>@test_int_x86_avx512_mask_pmov_qb_512(<8 x i64> %x0, <16 x i8> %
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 80) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[TMP1]], <16 x i8> [[TMP2]], i8 -1)
+; CHECK-NEXT: [[_MSPROP2:%.*]] = or <16 x i8> zeroinitializer, [[TMP4]]
; CHECK-NEXT: [[RES0:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[X0:%.*]], <16 x i8> [[X1:%.*]], i8 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[X0]], <16 x i8> [[X1]], i8 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
+; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[TMP1]], <16 x i8> [[TMP2]], i8 [[X2:%.*]])
+; CHECK-NEXT: [[TMP6:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i128 [[TMP6]] to <16 x i8>
+; CHECK-NEXT: [[_MSPROP4:%.*]] = or <16 x i8> [[TMP7]], [[TMP8]]
+; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[X0]], <16 x i8> [[X1]], i8 [[X2]])
+; CHECK-NEXT: [[TMP12:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[TMP1]], <16 x i8> zeroinitializer, i8 [[X2]])
+; CHECK-NEXT: [[TMP9:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast i128 [[TMP9]] to <16 x i8>
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP5]], [[TMP12]]
; CHECK-NEXT: [[RES2:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[X0]], <16 x i8> zeroinitializer, i8 [[X2]])
+; CHECK-NEXT: [[_MSPROP3:%.*]] = or <16 x i8> [[_MSPROP2]], [[_MSPROP4]]
; CHECK-NEXT: [[RES3:%.*]] = add <16 x i8> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> [[_MSPROP3]], [[_MSPROP]]
; CHECK-NEXT: [[RES4:%.*]] = add <16 x i8> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <16 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i8> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[RES4]]
;
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> %x0, <16 x i8> %x1, i8 -1)
@@ -6657,43 +6679,24 @@ define <16 x i8>@test_int_x86_avx512_mask_pmovs_qb_512(<8 x i64> %x0, <16 x i8>
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 80) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[TMP1]], <16 x i8> [[TMP2]], i8 -1)
+; CHECK-NEXT: [[TMP5:%.*]] = or <16 x i8> zeroinitializer, [[TMP4]]
; CHECK-NEXT: [[RES0:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovs.qb.512(<8 x i64> [[X0:%.*]], <16 x i8> [[X1:%.*]], i8 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovs.qb.512(<8 x i64> [[X0]], <16 x i8> [[X1]], i8 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
+; CHECK-NEXT: [[TMP11:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[TMP1]], <16 x i8> [[TMP2]], i8 [[X2:%.*]])
+; CHECK-NEXT: [[TMP6:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i128 [[TMP6]] to <16 x i8>
+; CHECK-NEXT: [[TMP12:%.*]] = or <16 x i8> [[TMP7]], [[TMP11]]
+; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovs.qb.512(<8 x i64> [[X0]], <16 x i8> [[X1]], i8 [[X2]])
+; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[TMP1]], <16 x i8> zeroinitializer, i8 [[X2]])
+; CHECK-NEXT: [[TMP9:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast i128 [[TMP9]] to <16 x i8>
+; CHECK-NEXT: [[TMP19:%.*]] = or <16 x i8> [[TMP10]], [[TMP8]]
; CHECK-NEXT: [[RES2:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovs.qb.512(<8 x i64> [[X0]], <16 x i8> zeroinitializer, i8 [[X2]])
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP5]], [[TMP12]]
; CHECK-NEXT: [[RES3:%.*]] = add <16 x i8> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> [[_MSPROP]], [[TMP19]]
; CHECK-NEXT: [[RES4:%.*]] = add <16 x i8> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <16 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i8> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[RES4]]
;
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.qb.512(<8 x i64> %x0, <16 x i8> %x1, i8 -1)
@@ -6749,43 +6752,24 @@ define <16 x i8>@test_int_x86_avx512_mask_pmovus_qb_512(<8 x i64> %x0, <16 x i8>
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 80) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[TMP1]], <16 x i8> [[TMP2]], i8 -1)
+; CHECK-NEXT: [[TMP5:%.*]] = or <16 x i8> zeroinitializer, [[TMP4]]
; CHECK-NEXT: [[RES0:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovus.qb.512(<8 x i64> [[X0:%.*]], <16 x i8> [[X1:%.*]], i8 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovus.qb.512(<8 x i64> [[X0]], <16 x i8> [[X1]], i8 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
+; CHECK-NEXT: [[TMP11:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[TMP1]], <16 x i8> [[TMP2]], i8 [[X2:%.*]])
+; CHECK-NEXT: [[TMP6:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i128 [[TMP6]] to <16 x i8>
+; CHECK-NEXT: [[TMP12:%.*]] = or <16 x i8> [[TMP7]], [[TMP11]]
+; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovus.qb.512(<8 x i64> [[X0]], <16 x i8> [[X1]], i8 [[X2]])
+; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> [[TMP1]], <16 x i8> zeroinitializer, i8 [[X2]])
+; CHECK-NEXT: [[TMP9:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast i128 [[TMP9]] to <16 x i8>
+; CHECK-NEXT: [[TMP19:%.*]] = or <16 x i8> [[TMP10]], [[TMP8]]
; CHECK-NEXT: [[RES2:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovus.qb.512(<8 x i64> [[X0]], <16 x i8> zeroinitializer, i8 [[X2]])
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP5]], [[TMP12]]
; CHECK-NEXT: [[RES3:%.*]] = add <16 x i8> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> [[_MSPROP]], [[TMP19]]
; CHECK-NEXT: [[RES4:%.*]] = add <16 x i8> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <16 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i8> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[RES4]]
;
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.qb.512(<8 x i64> %x0, <16 x i8> %x1, i8 -1)
@@ -6841,43 +6825,24 @@ define <8 x i16>@test_int_x86_avx512_mask_pmov_qw_512(<8 x i64> %x0, <8 x i16> %
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i16>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 80) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <8 x i16> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP8:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[TMP1]], <8 x i16> [[TMP2]], i8 -1)
+; CHECK-NEXT: [[_MSPROP2:%.*]] = or <8 x i16> zeroinitializer, [[TMP8]]
; CHECK-NEXT: [[RES0:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[X0:%.*]], <8 x i16> [[X1:%.*]], i8 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <8 x i16> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[X0]], <8 x i16> [[X1]], i8 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
-; CHECK-NEXT: [[RES2:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[X0]], <8 x i16> zeroinitializer, i8 [[X2]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[TMP1]], <8 x i16> [[TMP2]], i8 [[TMP6:%.*]])
+; CHECK-NEXT: [[TMP10:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i128 [[TMP10]] to <8 x i16>
+; CHECK-NEXT: [[_MSPROP4:%.*]] = or <8 x i16> [[TMP7]], [[TMP5]]
+; CHECK-NEXT: [[RES1:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[X0]], <8 x i16> [[X1]], i8 [[TMP6]])
+; CHECK-NEXT: [[TMP9:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[TMP1]], <8 x i16> zeroinitializer, i8 [[TMP6]])
+; CHECK-NEXT: [[TMP11:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast i128 [[TMP11]] to <8 x i16>
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i16> [[TMP4]], [[TMP9]]
+; CHECK-NEXT: [[RES2:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[X0]], <8 x i16> zeroinitializer, i8 [[TMP6]])
+; CHECK-NEXT: [[_MSPROP3:%.*]] = or <8 x i16> [[_MSPROP2]], [[_MSPROP4]]
; CHECK-NEXT: [[RES3:%.*]] = add <8 x i16> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <8 x i16> [[_MSPROP3]], [[_MSPROP]]
; CHECK-NEXT: [[RES4:%.*]] = add <8 x i16> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <8 x i16> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <8 x i16> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i16> [[RES4]]
;
%res0 = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> %x0, <8 x i16> %x1, i8 -1)
@@ -6933,43 +6898,24 @@ define <8 x i16>@test_int_x86_avx512_mask_pmovs_qw_512(<8 x i64> %x0, <8 x i16>
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i16>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 80) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <8 x i16> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP11:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[TMP1]], <8 x i16> [[TMP2]], i8 -1)
+; CHECK-NEXT: [[TMP4:%.*]] = or <8 x i16> zeroinitializer, [[TMP11]]
; CHECK-NEXT: [[RES0:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64> [[X0:%.*]], <8 x i16> [[X1:%.*]], i8 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <8 x i16> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64> [[X0]], <8 x i16> [[X1]], i8 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
-; CHECK-NEXT: [[RES2:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64> [[X0]], <8 x i16> zeroinitializer, i8 [[X2]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[TMP1]], <8 x i16> [[TMP2]], i8 [[TMP6:%.*]])
+; CHECK-NEXT: [[TMP12:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i128 [[TMP12]] to <8 x i16>
+; CHECK-NEXT: [[TMP9:%.*]] = or <8 x i16> [[TMP7]], [[TMP5]]
+; CHECK-NEXT: [[RES1:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64> [[X0]], <8 x i16> [[X1]], i8 [[TMP6]])
+; CHECK-NEXT: [[TMP8:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[TMP1]], <8 x i16> zeroinitializer, i8 [[TMP6]])
+; CHECK-NEXT: [[TMP13:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast i128 [[TMP13]] to <8 x i16>
+; CHECK-NEXT: [[TMP14:%.*]] = or <8 x i16> [[TMP10]], [[TMP8]]
+; CHECK-NEXT: [[RES2:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64> [[X0]], <8 x i16> zeroinitializer, i8 [[TMP6]])
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i16> [[TMP4]], [[TMP9]]
; CHECK-NEXT: [[RES3:%.*]] = add <8 x i16> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <8 x i16> [[_MSPROP]], [[TMP14]]
; CHECK-NEXT: [[RES4:%.*]] = add <8 x i16> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <8 x i16> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <8 x i16> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i16> [[RES4]]
;
%res0 = call <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64> %x0, <8 x i16> %x1, i8 -1)
@@ -7025,43 +6971,24 @@ define <8 x i16>@test_int_x86_avx512_mask_pmovus_qw_512(<8 x i64> %x0, <8 x i16>
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i16>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 80) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <8 x i16> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP11:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[TMP1]], <8 x i16> [[TMP2]], i8 -1)
+; CHECK-NEXT: [[TMP4:%.*]] = or <8 x i16> zeroinitializer, [[TMP11]]
; CHECK-NEXT: [[RES0:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64> [[X0:%.*]], <8 x i16> [[X1:%.*]], i8 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <8 x i16> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64> [[X0]], <8 x i16> [[X1]], i8 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
-; CHECK-NEXT: [[RES2:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64> [[X0]], <8 x i16> zeroinitializer, i8 [[X2]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[TMP1]], <8 x i16> [[TMP2]], i8 [[TMP6:%.*]])
+; CHECK-NEXT: [[TMP12:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i128 [[TMP12]] to <8 x i16>
+; CHECK-NEXT: [[TMP9:%.*]] = or <8 x i16> [[TMP7]], [[TMP5]]
+; CHECK-NEXT: [[RES1:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64> [[X0]], <8 x i16> [[X1]], i8 [[TMP6]])
+; CHECK-NEXT: [[TMP8:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> [[TMP1]], <8 x i16> zeroinitializer, i8 [[TMP6]])
+; CHECK-NEXT: [[TMP13:%.*]] = zext i8 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast i128 [[TMP13]] to <8 x i16>
+; CHECK-NEXT: [[TMP14:%.*]] = or <8 x i16> [[TMP10]], [[TMP8]]
+; CHECK-NEXT: [[RES2:%.*]] = call <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64> [[X0]], <8 x i16> zeroinitializer, i8 [[TMP6]])
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i16> [[TMP4]], [[TMP9]]
; CHECK-NEXT: [[RES3:%.*]] = add <8 x i16> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <8 x i16> [[_MSPROP]], [[TMP14]]
; CHECK-NEXT: [[RES4:%.*]] = add <8 x i16> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <8 x i16> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <8 x i16> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i16> [[RES4]]
;
%res0 = call <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64> %x0, <8 x i16> %x1, i8 -1)
@@ -7215,18 +7142,10 @@ define <8 x i32>@test_int_x86_avx512_pmovs_qd_512(<8 x i64> %x0, <8 x i32> %x1)
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP3]], 0
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i32> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP4]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP5:%.*]], label [[TMP6:%.*]], !prof [[PROF1]]
-; CHECK: 5:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 6:
+; CHECK-NEXT: [[TMP3:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
+; CHECK-NEXT: [[TMP4:%.*]] = select <8 x i1> splat (i1 true), <8 x i32> [[TMP3]], <8 x i32> [[TMP2]]
; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> [[X1:%.*]], i8 -1)
-; CHECK-NEXT: store <8 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <8 x i32> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
;
%res = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 -1)
@@ -7237,22 +7156,12 @@ define <8 x i32>@test_int_x86_avx512_mask_pmovs_qd_512(<8 x i64> %x0, <8 x i32>
; CHECK-LABEL: @test_int_x86_avx512_mask_pmovs_qd_512(
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
-; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <8 x i32> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR3:%.*]] = or i1 [[_MSOR]], [[_MSCMP2]]
-; CHECK-NEXT: br i1 [[_MSOR3]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
-; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> [[X1:%.*]], i8 [[X2:%.*]])
-; CHECK-NEXT: store <8 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast i8 [[TMP4:%.*]] to <8 x i1>
+; CHECK-NEXT: [[TMP6:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
+; CHECK-NEXT: [[TMP7:%.*]] = select <8 x i1> [[TMP5]], <8 x i32> [[TMP6]], <8 x i32> [[TMP2]]
+; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> [[X1:%.*]], i8 [[TMP4]])
+; CHECK-NEXT: store <8 x i32> [[TMP7]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
;
%res = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2)
@@ -7262,19 +7171,12 @@ define <8 x i32>@test_int_x86_avx512_mask_pmovs_qd_512(<8 x i64> %x0, <8 x i32>
define <8 x i32>@test_int_x86_avx512_maskz_pmovs_qd_512(<8 x i64> %x0, i8 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_maskz_pmovs_qd_512(
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
-; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP3]], 0
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i8 [[TMP2]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP4:%.*]], label [[TMP5:%.*]], !prof [[PROF1]]
-; CHECK: 4:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 5:
-; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> zeroinitializer, i8 [[X2:%.*]])
-; CHECK-NEXT: store <8 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast i8 [[TMP3:%.*]] to <8 x i1>
+; CHECK-NEXT: [[TMP5:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
+; CHECK-NEXT: [[TMP6:%.*]] = select <8 x i1> [[TMP4]], <8 x i32> [[TMP5]], <8 x i32> zeroinitializer
+; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> zeroinitializer, i8 [[TMP3]])
+; CHECK-NEXT: store <8 x i32> [[TMP6]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
;
%res = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> %x0, <8 x i32> zeroinitializer, i8 %x2)
@@ -7325,18 +7227,10 @@ define <8 x i32>@test_int_x86_avx512_pmovus_qd_512(<8 x i64> %x0, <8 x i32> %x1)
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP3]], 0
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i32> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP4]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP5:%.*]], label [[TMP6:%.*]], !prof [[PROF1]]
-; CHECK: 5:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 6:
+; CHECK-NEXT: [[TMP3:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
+; CHECK-NEXT: [[TMP4:%.*]] = select <8 x i1> splat (i1 true), <8 x i32> [[TMP3]], <8 x i32> [[TMP2]]
; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> [[X1:%.*]], i8 -1)
-; CHECK-NEXT: store <8 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <8 x i32> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
;
%res = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 -1)
@@ -7347,22 +7241,12 @@ define <8 x i32>@test_int_x86_avx512_mask_pmovus_qd_512(<8 x i64> %x0, <8 x i32>
; CHECK-LABEL: @test_int_x86_avx512_mask_pmovus_qd_512(
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
-; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <8 x i32> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR3:%.*]] = or i1 [[_MSOR]], [[_MSCMP2]]
-; CHECK-NEXT: br i1 [[_MSOR3]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
-; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> [[X1:%.*]], i8 [[X2:%.*]])
-; CHECK-NEXT: store <8 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast i8 [[TMP4:%.*]] to <8 x i1>
+; CHECK-NEXT: [[TMP6:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
+; CHECK-NEXT: [[TMP7:%.*]] = select <8 x i1> [[TMP5]], <8 x i32> [[TMP6]], <8 x i32> [[TMP2]]
+; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> [[X1:%.*]], i8 [[TMP4]])
+; CHECK-NEXT: store <8 x i32> [[TMP7]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
;
%res = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2)
@@ -7372,19 +7256,12 @@ define <8 x i32>@test_int_x86_avx512_mask_pmovus_qd_512(<8 x i64> %x0, <8 x i32>
define <8 x i32>@test_int_x86_avx512_maskz_pmovus_qd_512(<8 x i64> %x0, i8 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_maskz_pmovus_qd_512(
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
-; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP3]], 0
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i8 [[TMP2]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP4:%.*]], label [[TMP5:%.*]], !prof [[PROF1]]
-; CHECK: 4:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 5:
-; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> zeroinitializer, i8 [[X2:%.*]])
-; CHECK-NEXT: store <8 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast i8 [[TMP3:%.*]] to <8 x i1>
+; CHECK-NEXT: [[TMP5:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
+; CHECK-NEXT: [[TMP6:%.*]] = select <8 x i1> [[TMP4]], <8 x i32> [[TMP5]], <8 x i32> zeroinitializer
+; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> zeroinitializer, i8 [[TMP3]])
+; CHECK-NEXT: store <8 x i32> [[TMP6]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
;
%res = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> %x0, <8 x i32> zeroinitializer, i8 %x2)
@@ -7436,43 +7313,24 @@ define <16 x i8>@test_int_x86_avx512_mask_pmov_db_512(<16 x i32> %x0, <16 x i8>
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i16, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 80) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[TMP1]], <16 x i8> [[TMP2]], i16 -1)
+; CHECK-NEXT: [[_MSPROP2:%.*]] = or <16 x i8> zeroinitializer, [[TMP8]]
; CHECK-NEXT: [[RES0:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[X0:%.*]], <16 x i8> [[X1:%.*]], i16 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[X0]], <16 x i8> [[X1]], i16 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
-; CHECK-NEXT: [[RES2:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[X0]], <16 x i8> zeroinitializer, i16 [[X2]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[TMP1]], <16 x i8> [[TMP2]], i16 [[TMP6:%.*]])
+; CHECK-NEXT: [[TMP10:%.*]] = zext i16 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i128 [[TMP10]] to <16 x i8>
+; CHECK-NEXT: [[_MSPROP4:%.*]] = or <16 x i8> [[TMP7]], [[TMP5]]
+; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[X0]], <16 x i8> [[X1]], i16 [[TMP6]])
+; CHECK-NEXT: [[TMP9:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[TMP1]], <16 x i8> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[TMP11:%.*]] = zext i16 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast i128 [[TMP11]] to <16 x i8>
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP4]], [[TMP9]]
+; CHECK-NEXT: [[RES2:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[X0]], <16 x i8> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[_MSPROP3:%.*]] = or <16 x i8> [[_MSPROP2]], [[_MSPROP4]]
; CHECK-NEXT: [[RES3:%.*]] = add <16 x i8> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> [[_MSPROP3]], [[_MSPROP]]
; CHECK-NEXT: [[RES4:%.*]] = add <16 x i8> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <16 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i8> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[RES4]]
;
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> %x0, <16 x i8> %x1, i16 -1)
@@ -7528,43 +7386,24 @@ define <16 x i8>@test_int_x86_avx512_mask_pmovs_db_512(<16 x i32> %x0, <16 x i8>
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i16, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 80) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP11:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[TMP1]], <16 x i8> [[TMP2]], i16 -1)
+; CHECK-NEXT: [[TMP4:%.*]] = or <16 x i8> zeroinitializer, [[TMP11]]
; CHECK-NEXT: [[RES0:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> [[X0:%.*]], <16 x i8> [[X1:%.*]], i16 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> [[X0]], <16 x i8> [[X1]], i16 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
-; CHECK-NEXT: [[RES2:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> [[X0]], <16 x i8> zeroinitializer, i16 [[X2]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[TMP1]], <16 x i8> [[TMP2]], i16 [[TMP6:%.*]])
+; CHECK-NEXT: [[TMP12:%.*]] = zext i16 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i128 [[TMP12]] to <16 x i8>
+; CHECK-NEXT: [[TMP9:%.*]] = or <16 x i8> [[TMP7]], [[TMP5]]
+; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> [[X0]], <16 x i8> [[X1]], i16 [[TMP6]])
+; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[TMP1]], <16 x i8> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[TMP13:%.*]] = zext i16 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast i128 [[TMP13]] to <16 x i8>
+; CHECK-NEXT: [[TMP14:%.*]] = or <16 x i8> [[TMP10]], [[TMP8]]
+; CHECK-NEXT: [[RES2:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> [[X0]], <16 x i8> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP4]], [[TMP9]]
; CHECK-NEXT: [[RES3:%.*]] = add <16 x i8> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> [[_MSPROP]], [[TMP14]]
; CHECK-NEXT: [[RES4:%.*]] = add <16 x i8> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <16 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i8> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[RES4]]
;
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> %x0, <16 x i8> %x1, i16 -1)
@@ -7620,43 +7459,24 @@ define <16 x i8>@test_int_x86_avx512_mask_pmovus_db_512(<16 x i32> %x0, <16 x i8
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i16, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 80) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP11:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[TMP1]], <16 x i8> [[TMP2]], i16 -1)
+; CHECK-NEXT: [[TMP4:%.*]] = or <16 x i8> zeroinitializer, [[TMP11]]
; CHECK-NEXT: [[RES0:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32> [[X0:%.*]], <16 x i8> [[X1:%.*]], i16 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32> [[X0]], <16 x i8> [[X1]], i16 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
-; CHECK-NEXT: [[RES2:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32> [[X0]], <16 x i8> zeroinitializer, i16 [[X2]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[TMP1]], <16 x i8> [[TMP2]], i16 [[TMP6:%.*]])
+; CHECK-NEXT: [[TMP12:%.*]] = zext i16 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i128 [[TMP12]] to <16 x i8>
+; CHECK-NEXT: [[TMP9:%.*]] = or <16 x i8> [[TMP7]], [[TMP5]]
+; CHECK-NEXT: [[RES1:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32> [[X0]], <16 x i8> [[X1]], i16 [[TMP6]])
+; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> [[TMP1]], <16 x i8> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[TMP13:%.*]] = zext i16 [[TMP3]] to i128
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast i128 [[TMP13]] to <16 x i8>
+; CHECK-NEXT: [[TMP14:%.*]] = or <16 x i8> [[TMP10]], [[TMP8]]
+; CHECK-NEXT: [[RES2:%.*]] = call <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32> [[X0]], <16 x i8> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i8> [[TMP4]], [[TMP9]]
; CHECK-NEXT: [[RES3:%.*]] = add <16 x i8> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i8> [[_MSPROP]], [[TMP14]]
; CHECK-NEXT: [[RES4:%.*]] = add <16 x i8> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <16 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i8> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i8> [[RES4]]
;
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32> %x0, <16 x i8> %x1, i16 -1)
@@ -7712,43 +7532,24 @@ define <16 x i16>@test_int_x86_avx512_mask_pmov_dw_512(<16 x i32> %x0, <16 x i16
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i16>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i16, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <16 x i16> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[TMP1]], <16 x i16> [[TMP2]], i16 -1)
+; CHECK-NEXT: [[_MSPROP2:%.*]] = or <16 x i16> zeroinitializer, [[TMP8]]
; CHECK-NEXT: [[RES0:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[X0:%.*]], <16 x i16> [[X1:%.*]], i16 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i16> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i256 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[X0]], <16 x i16> [[X1]], i16 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
-; CHECK-NEXT: [[RES2:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[X0]], <16 x i16> zeroinitializer, i16 [[X2]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[TMP1]], <16 x i16> [[TMP2]], i16 [[TMP6:%.*]])
+; CHECK-NEXT: [[TMP10:%.*]] = zext i16 [[TMP3]] to i256
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i256 [[TMP10]] to <16 x i16>
+; CHECK-NEXT: [[_MSPROP4:%.*]] = or <16 x i16> [[TMP7]], [[TMP5]]
+; CHECK-NEXT: [[RES1:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[X0]], <16 x i16> [[X1]], i16 [[TMP6]])
+; CHECK-NEXT: [[TMP9:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[TMP1]], <16 x i16> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[TMP11:%.*]] = zext i16 [[TMP3]] to i256
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast i256 [[TMP11]] to <16 x i16>
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i16> [[TMP4]], [[TMP9]]
+; CHECK-NEXT: [[RES2:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[X0]], <16 x i16> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[_MSPROP3:%.*]] = or <16 x i16> [[_MSPROP2]], [[_MSPROP4]]
; CHECK-NEXT: [[RES3:%.*]] = add <16 x i16> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i16> [[_MSPROP3]], [[_MSPROP]]
; CHECK-NEXT: [[RES4:%.*]] = add <16 x i16> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <16 x i16> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i16> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i16> [[RES4]]
;
%res0 = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> %x0, <16 x i16> %x1, i16 -1)
@@ -7804,43 +7605,24 @@ define <16 x i16>@test_int_x86_avx512_mask_pmovs_dw_512(<16 x i32> %x0, <16 x i1
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i16>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i16, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <16 x i16> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP11:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[TMP1]], <16 x i16> [[TMP2]], i16 -1)
+; CHECK-NEXT: [[TMP4:%.*]] = or <16 x i16> zeroinitializer, [[TMP11]]
; CHECK-NEXT: [[RES0:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32> [[X0:%.*]], <16 x i16> [[X1:%.*]], i16 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i16> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i256 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32> [[X0]], <16 x i16> [[X1]], i16 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
-; CHECK-NEXT: [[RES2:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32> [[X0]], <16 x i16> zeroinitializer, i16 [[X2]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[TMP1]], <16 x i16> [[TMP2]], i16 [[TMP6:%.*]])
+; CHECK-NEXT: [[TMP12:%.*]] = zext i16 [[TMP3]] to i256
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i256 [[TMP12]] to <16 x i16>
+; CHECK-NEXT: [[TMP9:%.*]] = or <16 x i16> [[TMP7]], [[TMP5]]
+; CHECK-NEXT: [[RES1:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32> [[X0]], <16 x i16> [[X1]], i16 [[TMP6]])
+; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[TMP1]], <16 x i16> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[TMP13:%.*]] = zext i16 [[TMP3]] to i256
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast i256 [[TMP13]] to <16 x i16>
+; CHECK-NEXT: [[TMP14:%.*]] = or <16 x i16> [[TMP10]], [[TMP8]]
+; CHECK-NEXT: [[RES2:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32> [[X0]], <16 x i16> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i16> [[TMP4]], [[TMP9]]
; CHECK-NEXT: [[RES3:%.*]] = add <16 x i16> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i16> [[_MSPROP]], [[TMP14]]
; CHECK-NEXT: [[RES4:%.*]] = add <16 x i16> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <16 x i16> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i16> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i16> [[RES4]]
;
%res0 = call <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32> %x0, <16 x i16> %x1, i16 -1)
@@ -7896,43 +7678,24 @@ define <16 x i16>@test_int_x86_avx512_mask_pmovus_dw_512(<16 x i32> %x0, <16 x i
; CHECK-NEXT: [[TMP2:%.*]] = load <16 x i16>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP3:%.*]] = load i16, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <16 x i16> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
+; CHECK-NEXT: [[TMP11:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[TMP1]], <16 x i16> [[TMP2]], i16 -1)
+; CHECK-NEXT: [[TMP4:%.*]] = or <16 x i16> zeroinitializer, [[TMP11]]
; CHECK-NEXT: [[RES0:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32> [[X0:%.*]], <16 x i16> [[X1:%.*]], i16 -1)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i16> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP3:%.*]] = icmp ne i256 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR4:%.*]] = or i1 [[_MSCMP2]], [[_MSCMP3]]
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSOR4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label [[TMP10:%.*]], label [[TMP11:%.*]], !prof [[PROF1]]
-; CHECK: 10:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 11:
-; CHECK-NEXT: [[RES1:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32> [[X0]], <16 x i16> [[X1]], i16 [[X2:%.*]])
-; CHECK-NEXT: [[TMP12:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP7:%.*]] = icmp ne i512 [[TMP12]], 0
-; CHECK-NEXT: [[_MSCMP8:%.*]] = icmp ne i16 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR9:%.*]] = or i1 [[_MSCMP7]], [[_MSCMP8]]
-; CHECK-NEXT: br i1 [[_MSOR9]], label [[TMP13:%.*]], label [[TMP14:%.*]], !prof [[PROF1]]
-; CHECK: 13:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
-; CHECK-NEXT: unreachable
-; CHECK: 14:
-; CHECK-NEXT: [[RES2:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32> [[X0]], <16 x i16> zeroinitializer, i16 [[X2]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[TMP1]], <16 x i16> [[TMP2]], i16 [[TMP6:%.*]])
+; CHECK-NEXT: [[TMP12:%.*]] = zext i16 [[TMP3]] to i256
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast i256 [[TMP12]] to <16 x i16>
+; CHECK-NEXT: [[TMP9:%.*]] = or <16 x i16> [[TMP7]], [[TMP5]]
+; CHECK-NEXT: [[RES1:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32> [[X0]], <16 x i16> [[X1]], i16 [[TMP6]])
+; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> [[TMP1]], <16 x i16> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[TMP13:%.*]] = zext i16 [[TMP3]] to i256
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast i256 [[TMP13]] to <16 x i16>
+; CHECK-NEXT: [[TMP14:%.*]] = or <16 x i16> [[TMP10]], [[TMP8]]
+; CHECK-NEXT: [[RES2:%.*]] = call <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32> [[X0]], <16 x i16> zeroinitializer, i16 [[TMP6]])
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <16 x i16> [[TMP4]], [[TMP9]]
; CHECK-NEXT: [[RES3:%.*]] = add <16 x i16> [[RES0]], [[RES1]]
+; CHECK-NEXT: [[_MSPROP1:%.*]] = or <16 x i16> [[_MSPROP]], [[TMP14]]
; CHECK-NEXT: [[RES4:%.*]] = add <16 x i16> [[RES3]], [[RES2]]
-; CHECK-NEXT: store <16 x i16> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i16> [[_MSPROP1]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x i16> [[RES4]]
;
%res0 = call <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32> %x0, <16 x i16> %x1, i16 -1)
diff --git a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512bw-intrinsics.ll b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512bw-intrinsics.ll
index 3f09e54a0224d..72320730908e2 100644
--- a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512bw-intrinsics.ll
+++ b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512bw-intrinsics.ll
@@ -6,8 +6,6 @@
; Strictly handled:
; - llvm.x86.avx512.dbpsadbw.512
; - llvm.x86.avx512.ktestc.d, llvm.x86.avx512.ktestc.q, llvm.x86.avx512.ktestz.d, llvm.x86.avx512.ktestz.q
-; - llvm.x86.avx512.mask.pmovs.wb.512, llvm.x86.avx512.mask.pmovs.wb.mem.512
-; - llvm.x86.avx512.mask.pmovus.wb.512, llvm.x86.avx512.mask.pmovus.wb.mem.512
; - llvm.x86.avx512.mask.pmov.wb.mem.512
; - llvm.x86.avx512.packssdw.512, llvm.x86.avx512.packsswb.512
; - llvm.x86.avx512.packusdw.512, llvm.x86.avx512.packuswb.512
@@ -2478,18 +2476,10 @@ define <32 x i8>@test_int_x86_avx512_pmovs_wb_512(<32 x i16> %x0, <32 x i8> %x1)
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <32 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <32 x i16> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP3]], 0
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <32 x i8> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP4]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP5:%.*]], label [[TMP6:%.*]], !prof [[PROF1]]
-; CHECK: 5:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
-; CHECK-NEXT: unreachable
-; CHECK: 6:
+; CHECK-NEXT: [[TMP3:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
+; CHECK-NEXT: [[TMP4:%.*]] = select <32 x i1> splat (i1 true), <32 x i8> [[TMP3]], <32 x i8> [[TMP2]]
; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> [[X1:%.*]], i32 -1)
-; CHECK-NEXT: store <32 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <32 x i8> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
;
%res = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> %x0, <32 x i8> %x1, i32 -1)
@@ -2500,22 +2490,12 @@ define <32 x i8>@test_int_x86_avx512_mask_pmovs_wb_512(<32 x i16> %x0, <32 x i8>
; CHECK-LABEL: @test_int_x86_avx512_mask_pmovs_wb_512(
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <32 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
-; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <32 x i16> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <32 x i8> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i32 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR3:%.*]] = or i1 [[_MSOR]], [[_MSCMP2]]
-; CHECK-NEXT: br i1 [[_MSOR3]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
-; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> [[X1:%.*]], i32 [[X2:%.*]])
-; CHECK-NEXT: store <32 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32 [[X2:%.*]] to <32 x i1>
+; CHECK-NEXT: [[TMP4:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
+; CHECK-NEXT: [[TMP5:%.*]] = select <32 x i1> [[TMP3]], <32 x i8> [[TMP4]], <32 x i8> [[TMP2]]
+; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> [[X1:%.*]], i32 [[X2]])
+; CHECK-NEXT: store <32 x i8> [[TMP5]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
;
%res = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> %x0, <32 x i8> %x1, i32 %x2)
@@ -2525,19 +2505,12 @@ define <32 x i8>@test_int_x86_avx512_mask_pmovs_wb_512(<32 x i16> %x0, <32 x i8>
define <32 x i8>@test_int_x86_avx512_maskz_pmovs_wb_512(<32 x i16> %x0, i32 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_maskz_pmovs_wb_512(
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
-; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <32 x i16> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP3]], 0
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i32 [[TMP2]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP4:%.*]], label [[TMP5:%.*]], !prof [[PROF1]]
-; CHECK: 4:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
-; CHECK-NEXT: unreachable
-; CHECK: 5:
-; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> zeroinitializer, i32 [[X2:%.*]])
-; CHECK-NEXT: store <32 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32 [[X2:%.*]] to <32 x i1>
+; CHECK-NEXT: [[TMP3:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
+; CHECK-NEXT: [[TMP4:%.*]] = select <32 x i1> [[TMP2]], <32 x i8> [[TMP3]], <32 x i8> zeroinitializer
+; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> zeroinitializer, i32 [[X2]])
+; CHECK-NEXT: store <32 x i8> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
;
%res = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> %x0, <32 x i8> zeroinitializer, i32 %x2)
@@ -2588,18 +2561,10 @@ define <32 x i8>@test_int_x86_avx512_pmovus_wb_512(<32 x i16> %x0, <32 x i8> %x1
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <32 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <32 x i16> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP3]], 0
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <32 x i8> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP4]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP5:%.*]], label [[TMP6:%.*]], !prof [[PROF1]]
-; CHECK: 5:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
-; CHECK-NEXT: unreachable
-; CHECK: 6:
+; CHECK-NEXT: [[TMP3:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
+; CHECK-NEXT: [[TMP4:%.*]] = select <32 x i1> splat (i1 true), <32 x i8> [[TMP3]], <32 x i8> [[TMP2]]
; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> [[X1:%.*]], i32 -1)
-; CHECK-NEXT: store <32 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <32 x i8> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
;
%res = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> %x0, <32 x i8> %x1, i32 -1)
@@ -2610,22 +2575,12 @@ define <32 x i8>@test_int_x86_avx512_mask_pmovus_wb_512(<32 x i16> %x0, <32 x i8
; CHECK-LABEL: @test_int_x86_avx512_mask_pmovus_wb_512(
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <32 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
-; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <32 x i16> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <32 x i8> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i32 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR3:%.*]] = or i1 [[_MSOR]], [[_MSCMP2]]
-; CHECK-NEXT: br i1 [[_MSOR3]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
-; CHECK: 6:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
-; CHECK-NEXT: unreachable
-; CHECK: 7:
-; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> [[X1:%.*]], i32 [[X2:%.*]])
-; CHECK-NEXT: store <32 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32 [[X2:%.*]] to <32 x i1>
+; CHECK-NEXT: [[TMP4:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
+; CHECK-NEXT: [[TMP5:%.*]] = select <32 x i1> [[TMP3]], <32 x i8> [[TMP4]], <32 x i8> [[TMP2]]
+; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> [[X1:%.*]], i32 [[X2]])
+; CHECK-NEXT: store <32 x i8> [[TMP5]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
;
%res = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> %x0, <32 x i8> %x1, i32 %x2)
@@ -2635,19 +2590,12 @@ define <32 x i8>@test_int_x86_avx512_mask_pmovus_wb_512(<32 x i16> %x0, <32 x i8
define <32 x i8>@test_int_x86_avx512_maskz_pmovus_wb_512(<32 x i16> %x0, i32 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_maskz_pmovus_wb_512(
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
-; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <32 x i16> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP3]], 0
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i32 [[TMP2]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
-; CHECK-NEXT: br i1 [[_MSOR]], label [[TMP4:%.*]], label [[TMP5:%.*]], !prof [[PROF1]]
-; CHECK: 4:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
-; CHECK-NEXT: unreachable
-; CHECK: 5:
-; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> zeroinitializer, i32 [[X2:%.*]])
-; CHECK-NEXT: store <32 x i8> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32 [[X2:%.*]] to <32 x i1>
+; CHECK-NEXT: [[TMP3:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
+; CHECK-NEXT: [[TMP4:%.*]] = select <32 x i1> [[TMP2]], <32 x i8> [[TMP3]], <32 x i8> zeroinitializer
+; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> zeroinitializer, i32 [[X2]])
+; CHECK-NEXT: store <32 x i8> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
;
%res = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> %x0, <32 x i8> zeroinitializer, i32 %x2)
>From 29e474f99a52e439387dc4e1abe522bf5b9ff5fb Mon Sep 17 00:00:00 2001
From: Thurston Dang <thurston at google.com>
Date: Tue, 8 Jul 2025 22:32:22 +0000
Subject: [PATCH 2/6] Explain false positive
---
llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
index 83a419eafc8ec..0b795c14e5dc9 100644
--- a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
@@ -4657,7 +4657,11 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
VectorType *ShadowType = maybeShrinkVectorShadowType(A, I);
// PMOV truncates; PMOVS/PMOVUS uses signed/unsigned saturation.
- // This handler treats them all as truncation.
+ // This handler treats them all as truncation, which leads to some rare
+ // false positives in the cases where the truncated bytes could
+ // unambiguously saturate the value e.g., if A = 10?????? ????????
+ // (big-endian), the unsigned saturated byte conversion is 1111111 i.e.,
+ // fully defined, but the truncated byte is ????????.
//
// TODO: use GetMinMaxUnsigned() to handle saturation precisely.
AShadow = IRB.CreateTrunc(AShadow, ShadowType, "_ms_trunc_shadow");
>From c2ee02cef06cc0f6a57def3d6ff3f536d0124413 Mon Sep 17 00:00:00 2001
From: Thurston Dang <thurston at google.com>
Date: Tue, 8 Jul 2025 22:33:17 +0000
Subject: [PATCH 3/6] clang-format
---
llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
index 0b795c14e5dc9..b6479232cc584 100644
--- a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
@@ -4644,7 +4644,8 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
// by using bitwise NOT before and after the ZExt.
if (ANumElements != OutputNumElements) {
Mask = IRB.CreateNot(Mask);
- Mask = IRB.CreateZExt(Mask, Type::getIntNTy(*MS.C, OutputNumElements), "_ms_widen_mask");
+ Mask = IRB.CreateZExt(Mask, Type::getIntNTy(*MS.C, OutputNumElements),
+ "_ms_widen_mask");
Mask = IRB.CreateNot(Mask);
}
Mask = IRB.CreateBitCast(
>From f4236abdff9619804eb25679d293677c2de4966d Mon Sep 17 00:00:00 2001
From: Thurston Dang <thurston at google.com>
Date: Tue, 8 Jul 2025 22:35:04 +0000
Subject: [PATCH 4/6] Tweak example
---
llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
index b6479232cc584..472dbaed0d6e7 100644
--- a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
@@ -4660,8 +4660,8 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
// PMOV truncates; PMOVS/PMOVUS uses signed/unsigned saturation.
// This handler treats them all as truncation, which leads to some rare
// false positives in the cases where the truncated bytes could
- // unambiguously saturate the value e.g., if A = 10?????? ????????
- // (big-endian), the unsigned saturated byte conversion is 1111111 i.e.,
+ // unambiguously saturate the value e.g., if A = ??????10 ????????
+ // (big-endian), the unsigned saturated byte conversion is 11111111 i.e.,
// fully defined, but the truncated byte is ????????.
//
// TODO: use GetMinMaxUnsigned() to handle saturation precisely.
>From f779e0b4e316fa16b69226357e032df28d28c070 Mon Sep 17 00:00:00 2001
From: Thurston Dang <thurston at google.com>
Date: Tue, 8 Jul 2025 22:52:34 +0000
Subject: [PATCH 5/6] Check shadow of mask
---
.../Instrumentation/MemorySanitizer.cpp | 1 +
.../MemorySanitizer/X86/avx512-intrinsics.ll | 28 +++++++++++++++++++
.../X86/avx512bw-intrinsics.ll | 28 +++++++++++++++++++
3 files changed, 57 insertions(+)
diff --git a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
index 472dbaed0d6e7..f536f61e62811 100644
--- a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
@@ -4632,6 +4632,7 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
assert(Mask->getType()->isIntegerTy());
assert(Mask->getType()->getScalarSizeInBits() == ANumElements);
+ insertCheckShadowOf(Mask, &I);
assert(I.getType() == WriteThrough->getType());
diff --git a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
index a8d32ce5b2719..1b42396ff31d5 100644
--- a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
+++ b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
@@ -7154,12 +7154,19 @@ define <8 x i32>@test_int_x86_avx512_pmovs_qd_512(<8 x i64> %x0, <8 x i32> %x1)
define <8 x i32>@test_int_x86_avx512_mask_pmovs_qd_512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_mask_pmovs_qd_512(
+; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i8 [[TMP4:%.*]] to <8 x i1>
; CHECK-NEXT: [[TMP6:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
; CHECK-NEXT: [[TMP7:%.*]] = select <8 x i1> [[TMP5]], <8 x i32> [[TMP6]], <8 x i32> [[TMP2]]
+; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i8 [[TMP3]], 0
+; CHECK-NEXT: br i1 [[_MSCMP]], label [[TMP8:%.*]], label [[TMP9:%.*]], !prof [[PROF1]]
+; CHECK: 6:
+; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
+; CHECK-NEXT: unreachable
+; CHECK: 7:
; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> [[X1:%.*]], i8 [[TMP4]])
; CHECK-NEXT: store <8 x i32> [[TMP7]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
@@ -7170,11 +7177,18 @@ define <8 x i32>@test_int_x86_avx512_mask_pmovs_qd_512(<8 x i64> %x0, <8 x i32>
define <8 x i32>@test_int_x86_avx512_maskz_pmovs_qd_512(<8 x i64> %x0, i8 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_maskz_pmovs_qd_512(
+; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i8 [[TMP3:%.*]] to <8 x i1>
; CHECK-NEXT: [[TMP5:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
; CHECK-NEXT: [[TMP6:%.*]] = select <8 x i1> [[TMP4]], <8 x i32> [[TMP5]], <8 x i32> zeroinitializer
+; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i8 [[TMP2]], 0
+; CHECK-NEXT: br i1 [[_MSCMP]], label [[TMP7:%.*]], label [[TMP8:%.*]], !prof [[PROF1]]
+; CHECK: 5:
+; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
+; CHECK-NEXT: unreachable
+; CHECK: 6:
; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> zeroinitializer, i8 [[TMP3]])
; CHECK-NEXT: store <8 x i32> [[TMP6]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
@@ -7239,12 +7253,19 @@ define <8 x i32>@test_int_x86_avx512_pmovus_qd_512(<8 x i64> %x0, <8 x i32> %x1)
define <8 x i32>@test_int_x86_avx512_mask_pmovus_qd_512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_mask_pmovus_qd_512(
+; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i8 [[TMP4:%.*]] to <8 x i1>
; CHECK-NEXT: [[TMP6:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
; CHECK-NEXT: [[TMP7:%.*]] = select <8 x i1> [[TMP5]], <8 x i32> [[TMP6]], <8 x i32> [[TMP2]]
+; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i8 [[TMP3]], 0
+; CHECK-NEXT: br i1 [[_MSCMP]], label [[TMP8:%.*]], label [[TMP9:%.*]], !prof [[PROF1]]
+; CHECK: 6:
+; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
+; CHECK-NEXT: unreachable
+; CHECK: 7:
; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> [[X1:%.*]], i8 [[TMP4]])
; CHECK-NEXT: store <8 x i32> [[TMP7]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
@@ -7255,11 +7276,18 @@ define <8 x i32>@test_int_x86_avx512_mask_pmovus_qd_512(<8 x i64> %x0, <8 x i32>
define <8 x i32>@test_int_x86_avx512_maskz_pmovus_qd_512(<8 x i64> %x0, i8 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_maskz_pmovus_qd_512(
+; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i8 [[TMP3:%.*]] to <8 x i1>
; CHECK-NEXT: [[TMP5:%.*]] = trunc <8 x i64> [[TMP1]] to <8 x i32>
; CHECK-NEXT: [[TMP6:%.*]] = select <8 x i1> [[TMP4]], <8 x i32> [[TMP5]], <8 x i32> zeroinitializer
+; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i8 [[TMP2]], 0
+; CHECK-NEXT: br i1 [[_MSCMP]], label [[TMP7:%.*]], label [[TMP8:%.*]], !prof [[PROF1]]
+; CHECK: 5:
+; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR10]]
+; CHECK-NEXT: unreachable
+; CHECK: 6:
; CHECK-NEXT: [[RES:%.*]] = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> [[X0:%.*]], <8 x i32> zeroinitializer, i8 [[TMP3]])
; CHECK-NEXT: store <8 x i32> [[TMP6]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i32> [[RES]]
diff --git a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512bw-intrinsics.ll b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512bw-intrinsics.ll
index 72320730908e2..636409fe20f83 100644
--- a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512bw-intrinsics.ll
+++ b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512bw-intrinsics.ll
@@ -2488,12 +2488,19 @@ define <32 x i8>@test_int_x86_avx512_pmovs_wb_512(<32 x i16> %x0, <32 x i8> %x1)
define <32 x i8>@test_int_x86_avx512_mask_pmovs_wb_512(<32 x i16> %x0, <32 x i8> %x1, i32 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_mask_pmovs_wb_512(
+; CHECK-NEXT: [[TMP8:%.*]] = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <32 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32 [[X2:%.*]] to <32 x i1>
; CHECK-NEXT: [[TMP4:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
; CHECK-NEXT: [[TMP5:%.*]] = select <32 x i1> [[TMP3]], <32 x i8> [[TMP4]], <32 x i8> [[TMP2]]
+; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i32 [[TMP8]], 0
+; CHECK-NEXT: br i1 [[_MSCMP]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
+; CHECK: 6:
+; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
+; CHECK-NEXT: unreachable
+; CHECK: 7:
; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> [[X1:%.*]], i32 [[X2]])
; CHECK-NEXT: store <32 x i8> [[TMP5]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
@@ -2504,11 +2511,18 @@ define <32 x i8>@test_int_x86_avx512_mask_pmovs_wb_512(<32 x i16> %x0, <32 x i8>
define <32 x i8>@test_int_x86_avx512_maskz_pmovs_wb_512(<32 x i16> %x0, i32 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_maskz_pmovs_wb_512(
+; CHECK-NEXT: [[TMP7:%.*]] = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32 [[X2:%.*]] to <32 x i1>
; CHECK-NEXT: [[TMP3:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
; CHECK-NEXT: [[TMP4:%.*]] = select <32 x i1> [[TMP2]], <32 x i8> [[TMP3]], <32 x i8> zeroinitializer
+; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i32 [[TMP7]], 0
+; CHECK-NEXT: br i1 [[_MSCMP]], label [[TMP5:%.*]], label [[TMP6:%.*]], !prof [[PROF1]]
+; CHECK: 5:
+; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
+; CHECK-NEXT: unreachable
+; CHECK: 6:
; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovs.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> zeroinitializer, i32 [[X2]])
; CHECK-NEXT: store <32 x i8> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
@@ -2573,12 +2587,19 @@ define <32 x i8>@test_int_x86_avx512_pmovus_wb_512(<32 x i16> %x0, <32 x i8> %x1
define <32 x i8>@test_int_x86_avx512_mask_pmovus_wb_512(<32 x i16> %x0, <32 x i8> %x1, i32 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_mask_pmovus_wb_512(
+; CHECK-NEXT: [[TMP8:%.*]] = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 96) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <32 x i8>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32 [[X2:%.*]] to <32 x i1>
; CHECK-NEXT: [[TMP4:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
; CHECK-NEXT: [[TMP5:%.*]] = select <32 x i1> [[TMP3]], <32 x i8> [[TMP4]], <32 x i8> [[TMP2]]
+; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i32 [[TMP8]], 0
+; CHECK-NEXT: br i1 [[_MSCMP]], label [[TMP6:%.*]], label [[TMP7:%.*]], !prof [[PROF1]]
+; CHECK: 6:
+; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
+; CHECK-NEXT: unreachable
+; CHECK: 7:
; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> [[X1:%.*]], i32 [[X2]])
; CHECK-NEXT: store <32 x i8> [[TMP5]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
@@ -2589,11 +2610,18 @@ define <32 x i8>@test_int_x86_avx512_mask_pmovus_wb_512(<32 x i16> %x0, <32 x i8
define <32 x i8>@test_int_x86_avx512_maskz_pmovus_wb_512(<32 x i16> %x0, i32 %x2) #0 {
; CHECK-LABEL: @test_int_x86_avx512_maskz_pmovus_wb_512(
+; CHECK-NEXT: [[TMP7:%.*]] = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32 [[X2:%.*]] to <32 x i1>
; CHECK-NEXT: [[TMP3:%.*]] = trunc <32 x i16> [[TMP1]] to <32 x i8>
; CHECK-NEXT: [[TMP4:%.*]] = select <32 x i1> [[TMP2]], <32 x i8> [[TMP3]], <32 x i8> zeroinitializer
+; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i32 [[TMP7]], 0
+; CHECK-NEXT: br i1 [[_MSCMP]], label [[TMP5:%.*]], label [[TMP6:%.*]], !prof [[PROF1]]
+; CHECK: 5:
+; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
+; CHECK-NEXT: unreachable
+; CHECK: 6:
; CHECK-NEXT: [[RES:%.*]] = call <32 x i8> @llvm.x86.avx512.mask.pmovus.wb.512(<32 x i16> [[X0:%.*]], <32 x i8> zeroinitializer, i32 [[X2]])
; CHECK-NEXT: store <32 x i8> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x i8> [[RES]]
>From e90c6e61704ed7a60690e14aa2832662515393ca Mon Sep 17 00:00:00 2001
From: Thurston Dang <thurston at google.com>
Date: Tue, 8 Jul 2025 22:53:04 +0000
Subject: [PATCH 6/6] Save money on newlines
---
llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp | 2 --
1 file changed, 2 deletions(-)
diff --git a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
index f536f61e62811..bb2eb99c00317 100644
--- a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
@@ -4667,13 +4667,11 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
//
// TODO: use GetMinMaxUnsigned() to handle saturation precisely.
AShadow = IRB.CreateTrunc(AShadow, ShadowType, "_ms_trunc_shadow");
-
AShadow = maybeExtendVectorShadowWithZeros(AShadow, I);
Value *WriteThroughShadow = getShadow(WriteThrough);
Value *Shadow = IRB.CreateSelect(Mask, AShadow, WriteThroughShadow);
-
setShadow(&I, Shadow);
setOriginForNaryOp(I);
}
More information about the llvm-commits
mailing list