[llvm] 7ad70d2 - [msan] Handle AVX512/AVX10 vrndscale (#160624)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Sep 25 17:59:09 PDT 2025
Author: Thurston Dang
Date: 2025-09-25T17:59:05-07:00
New Revision: 7ad70d2793ec9baba1f343d82c8457b744c74164
URL: https://github.com/llvm/llvm-project/commit/7ad70d2793ec9baba1f343d82c8457b744c74164
DIFF: https://github.com/llvm/llvm-project/commit/7ad70d2793ec9baba1f343d82c8457b744c74164.diff
LOG: [msan] Handle AVX512/AVX10 vrndscale (#160624)
Uses the updated handleAVX512VectorGenericMaskedFP() from
https://github.com/llvm/llvm-project/pull/159966
Added:
Modified:
llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
llvm/test/Instrumentation/MemorySanitizer/X86/avx512fp16-intrinsics.ll
llvm/test/Instrumentation/MemorySanitizer/X86/avx512vl-intrinsics.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
index d98c4e376a0b4..b988957dfbc08 100644
--- a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
@@ -6278,6 +6278,62 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
/*MaskIndex=*/2);
break;
+ // <32 x half> @llvm.x86.avx512fp16.mask.rndscale.ph.512
+ // (<32 x half>, i32, <32 x half>, i32, i32)
+ // <16 x half> @llvm.x86.avx512fp16.mask.rndscale.ph.256
+ // (<16 x half>, i32, <16 x half>, i32, i16)
+ // <8 x half> @llvm.x86.avx512fp16.mask.rndscale.ph.128
+ // (<8 x half>, i32, <8 x half>, i32, i8)
+ //
+ // <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512
+ // (<16 x float>, i32, <16 x float>, i16, i32)
+ // <8 x float> @llvm.x86.avx512.mask.rndscale.ps.256
+ // (<8 x float>, i32, <8 x float>, i8)
+ // <4 x float> @llvm.x86.avx512.mask.rndscale.ps.128
+ // (<4 x float>, i32, <4 x float>, i8)
+ //
+ // <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512
+ // (<8 x double>, i32, <8 x double>, i8, i32)
+ // A Imm WriteThru Mask Rounding
+ // <4 x double> @llvm.x86.avx512.mask.rndscale.pd.256
+ // (<4 x double>, i32, <4 x double>, i8)
+ // <2 x double> @llvm.x86.avx512.mask.rndscale.pd.128
+ // (<2 x double>, i32, <2 x double>, i8)
+ // A Imm WriteThru Mask
+ //
+ // <32 x bfloat> @llvm.x86.avx10.mask.rndscale.bf16.512
+ // (<32 x bfloat>, i32, <32 x bfloat>, i32)
+ // <16 x bfloat> @llvm.x86.avx10.mask.rndscale.bf16.256
+ // (<16 x bfloat>, i32, <16 x bfloat>, i16)
+ // <8 x bfloat> @llvm.x86.avx10.mask.rndscale.bf16.128
+ // (<8 x bfloat>, i32, <8 x bfloat>, i8)
+ //
+ // Not supported: three vectors
+ // - <8 x half> @llvm.x86.avx512fp16.mask.rndscale.sh
+ // (<8 x half>, <8 x half>,<8 x half>, i8, i32, i32)
+ // - <4 x float> @llvm.x86.avx512.mask.rndscale.ss
+ // (<4 x float>, <4 x float>, <4 x float>, i8, i32, i32)
+ // - <2 x double> @llvm.x86.avx512.mask.rndscale.sd
+ // (<2 x double>, <2 x double>, <2 x double>, i8, i32,
+ // i32)
+ // A B WriteThru Mask Imm
+ // Rounding
+ case Intrinsic::x86_avx512fp16_mask_rndscale_ph_512:
+ case Intrinsic::x86_avx512fp16_mask_rndscale_ph_256:
+ case Intrinsic::x86_avx512fp16_mask_rndscale_ph_128:
+ case Intrinsic::x86_avx512_mask_rndscale_ps_512:
+ case Intrinsic::x86_avx512_mask_rndscale_ps_256:
+ case Intrinsic::x86_avx512_mask_rndscale_ps_128:
+ case Intrinsic::x86_avx512_mask_rndscale_pd_512:
+ case Intrinsic::x86_avx512_mask_rndscale_pd_256:
+ case Intrinsic::x86_avx512_mask_rndscale_pd_128:
+ case Intrinsic::x86_avx10_mask_rndscale_bf16_512:
+ case Intrinsic::x86_avx10_mask_rndscale_bf16_256:
+ case Intrinsic::x86_avx10_mask_rndscale_bf16_128:
+ handleAVX512VectorGenericMaskedFP(I, /*AIndex=*/0, /*WriteThruIndex=*/2,
+ /*MaskIndex=*/3);
+ break;
+
// AVX512 FP16 Arithmetic
case Intrinsic::x86_avx512fp16_mask_add_sh_round:
case Intrinsic::x86_avx512fp16_mask_sub_sh_round:
diff --git a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
index b2a4f0e582f9e..d8f204f32cfd1 100644
--- a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
+++ b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512-intrinsics.ll
@@ -21,7 +21,7 @@
; - 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.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.maskz.fixupimm.pd.512, llvm.x86.avx512.maskz.fixupimm.ps.512, llvm.x86.avx512.maskz.fixupimm.sd, llvm.x86.avx512.maskz.fixupimm.ss
@@ -965,18 +965,11 @@ define <8 x double> @test7(<8 x double> %a) #0 {
; CHECK-LABEL: @test7(
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP2:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP2]], 0
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <8 x i64> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i512 [[TMP3]], 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: [[TMP2:%.*]] = icmp ne <8 x i64> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP3:%.*]] = sext <8 x i1> [[TMP2]] to <8 x i64>
+; CHECK-NEXT: [[TMP4:%.*]] = select <8 x i1> splat (i1 true), <8 x i64> [[TMP3]], <8 x i64> [[TMP1]]
; CHECK-NEXT: [[RES:%.*]] = call <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double> [[A:%.*]], i32 11, <8 x double> [[A]], i8 -1, i32 4)
-; CHECK-NEXT: store <8 x i64> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <8 x i64> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x double> [[RES]]
;
%res = call <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double> %a, i32 11, <8 x double> %a, i8 -1, i32 4)
@@ -989,18 +982,11 @@ define <16 x float> @test8(<16 x float> %a) #0 {
; CHECK-LABEL: @test8(
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i32>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP2:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i512 [[TMP2]], 0
-; CHECK-NEXT: [[TMP3:%.*]] = bitcast <16 x i32> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i512 [[TMP3]], 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: [[TMP2:%.*]] = icmp ne <16 x i32> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP3:%.*]] = sext <16 x i1> [[TMP2]] to <16 x i32>
+; CHECK-NEXT: [[TMP4:%.*]] = select <16 x i1> splat (i1 true), <16 x i32> [[TMP3]], <16 x i32> [[TMP1]]
; CHECK-NEXT: [[RES:%.*]] = call <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float> [[A:%.*]], i32 11, <16 x float> [[A]], i16 -1, i32 4)
-; CHECK-NEXT: store <16 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <16 x i32> [[TMP4]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <16 x float> [[RES]]
;
%res = call <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float> %a, i32 11, <16 x float> %a, i16 -1, i32 4)
diff --git a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512fp16-intrinsics.ll b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512fp16-intrinsics.ll
index e5cbe8c132238..8723b1005f8fc 100644
--- a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512fp16-intrinsics.ll
+++ b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512fp16-intrinsics.ll
@@ -17,7 +17,6 @@
; - llvm.x86.avx512fp16.mask.rcp.sh
; - llvm.x86.avx512fp16.mask.reduce.ph.512
; - llvm.x86.avx512fp16.mask.reduce.sh
-; - llvm.x86.avx512fp16.mask.rndscale.ph.512
; - llvm.x86.avx512fp16.mask.rndscale.sh
; - llvm.x86.avx512fp16.mask.rsqrt.sh
; - llvm.x86.avx512fp16.mask.scalef.ph.512
@@ -868,36 +867,28 @@ declare <32 x half> @llvm.x86.avx512fp16.mask.rndscale.ph.512(<32 x half>, i32,
define <32 x half>@test_int_x86_avx512_mask_rndscale_ph_512(<32 x half> %x0, <32 x half> %x2, i32 %x3) #0 {
; CHECK-LABEL: define <32 x half> @test_int_x86_avx512_mask_rndscale_ph_512(
; CHECK-SAME: <32 x half> [[X0:%.*]], <32 x half> [[X2:%.*]], i32 [[X3:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 128) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i16>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <32 x i16>, 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 128) 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 i16> [[TMP2]] to i512
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i512 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32 [[X3]] to <32 x i1>
+; CHECK-NEXT: [[TMP5:%.*]] = icmp ne <32 x i16> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP6:%.*]] = sext <32 x i1> [[TMP5]] to <32 x i16>
+; CHECK-NEXT: [[TMP7:%.*]] = select <32 x i1> [[TMP4]], <32 x i16> [[TMP6]], <32 x i16> [[TMP2]]
; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i32 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR3:%.*]] = or i1 [[_MSOR]], [[_MSCMP2]]
-; CHECK-NEXT: br i1 [[_MSOR3]], label %[[BB6:.*]], label %[[BB7:.*]], !prof [[PROF1]]
-; CHECK: [[BB6]]:
+; CHECK-NEXT: br i1 [[_MSCMP2]], label %[[BB8:.*]], label %[[BB9:.*]], !prof [[PROF1]]
+; CHECK: [[BB8]]:
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
; CHECK-NEXT: unreachable
-; CHECK: [[BB7]]:
+; CHECK: [[BB9]]:
; CHECK-NEXT: [[RES:%.*]] = call <32 x half> @llvm.x86.avx512fp16.mask.rndscale.ph.512(<32 x half> [[X0]], i32 8, <32 x half> [[X2]], i32 [[X3]], i32 4)
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <32 x i16> [[TMP1]] to i512
-; CHECK-NEXT: [[_MSCMP4:%.*]] = icmp ne i512 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <32 x i16> [[TMP2]] to i512
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i512 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSCMP4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label %[[BB10:.*]], label %[[BB11:.*]], !prof [[PROF1]]
-; CHECK: [[BB10]]:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR8]]
-; CHECK-NEXT: unreachable
-; CHECK: [[BB11]]:
+; CHECK-NEXT: [[TMP10:%.*]] = icmp ne <32 x i16> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP11:%.*]] = sext <32 x i1> [[TMP10]] to <32 x i16>
+; CHECK-NEXT: [[TMP12:%.*]] = select <32 x i1> splat (i1 true), <32 x i16> [[TMP11]], <32 x i16> [[TMP2]]
; CHECK-NEXT: [[RES1:%.*]] = call <32 x half> @llvm.x86.avx512fp16.mask.rndscale.ph.512(<32 x half> [[X0]], i32 4, <32 x half> [[X2]], i32 -1, i32 8)
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <32 x i16> [[TMP7]], [[TMP12]]
; CHECK-NEXT: [[RES2:%.*]] = fadd <32 x half> [[RES]], [[RES1]]
-; CHECK-NEXT: store <32 x i16> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <32 x i16> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <32 x half> [[RES2]]
;
%res = call <32 x half> @llvm.x86.avx512fp16.mask.rndscale.ph.512(<32 x half> %x0, i32 8, <32 x half> %x2, i32 %x3, i32 4)
diff --git a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512vl-intrinsics.ll b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512vl-intrinsics.ll
index 20114fe7d3151..d598142fe8dbf 100644
--- a/llvm/test/Instrumentation/MemorySanitizer/X86/avx512vl-intrinsics.ll
+++ b/llvm/test/Instrumentation/MemorySanitizer/X86/avx512vl-intrinsics.ll
@@ -54,8 +54,6 @@
; - llvm.x86.avx512.mask.pmovus.qd.mem.128, llvm.x86.avx512.mask.pmovus.qd.mem.256
; - llvm.x86.avx512.mask.pmovus.qw.128, llvm.x86.avx512.mask.pmovus.qw.256
; - llvm.x86.avx512.mask.pmovus.qw.mem.128, llvm.x86.avx512.mask.pmovus.qw.mem.256
-; - llvm.x86.avx512.mask.rndscale.pd.128, llvm.x86.avx512.mask.rndscale.pd.256
-; - llvm.x86.avx512.mask.rndscale.ps.128, llvm.x86.avx512.mask.rndscale.ps.256
; - llvm.x86.avx512.mask.scalef.pd.128, llvm.x86.avx512.mask.scalef.pd.256
; - llvm.x86.avx512.mask.scalef.ps.128, llvm.x86.avx512.mask.scalef.ps.256
; - llvm.x86.avx512.maskz.fixupimm.pd.128, llvm.x86.avx512.maskz.fixupimm.pd.256
@@ -7127,36 +7125,29 @@ define <2 x double>@test_int_x86_avx512_mask_rndscale_pd_128(<2 x double> %x0, <
;
; CHECK-LABEL: define <2 x double> @test_int_x86_avx512_mask_rndscale_pd_128(
; CHECK-SAME: <2 x double> [[X0:%.*]], <2 x double> [[X2:%.*]], i8 [[X3:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 32) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i64>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 16) to ptr), align 8
-; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 32) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <2 x i64> [[TMP1]] to i128
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i128 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <2 x i64> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[X3]] to i2
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast i2 [[TMP4]] to <2 x i1>
+; CHECK-NEXT: [[TMP6:%.*]] = icmp ne <2 x i64> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP7:%.*]] = sext <2 x i1> [[TMP6]] to <2 x i64>
+; CHECK-NEXT: [[TMP8:%.*]] = select <2 x i1> [[TMP5]], <2 x i64> [[TMP7]], <2 x i64> [[TMP2]]
; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR3:%.*]] = or i1 [[_MSOR]], [[_MSCMP2]]
-; CHECK-NEXT: br i1 [[_MSOR3]], label %[[BB6:.*]], label %[[BB7:.*]], !prof [[PROF1]]
-; CHECK: [[BB6]]:
+; CHECK-NEXT: br i1 [[_MSCMP2]], label %[[BB9:.*]], label %[[BB10:.*]], !prof [[PROF1]]
+; CHECK: [[BB9]]:
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR6]]
; CHECK-NEXT: unreachable
-; CHECK: [[BB7]]:
-; CHECK-NEXT: [[RES:%.*]] = call <2 x double> @llvm.x86.avx512.mask.rndscale.pd.128(<2 x double> [[X0]], i32 4, <2 x double> [[X2]], i8 [[X3]])
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <2 x i64> [[TMP1]] to i128
-; CHECK-NEXT: [[_MSCMP4:%.*]] = icmp ne i128 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <2 x i64> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSCMP4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label %[[BB10:.*]], label %[[BB11:.*]], !prof [[PROF1]]
; CHECK: [[BB10]]:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR6]]
-; CHECK-NEXT: unreachable
-; CHECK: [[BB11]]:
+; CHECK-NEXT: [[RES:%.*]] = call <2 x double> @llvm.x86.avx512.mask.rndscale.pd.128(<2 x double> [[X0]], i32 4, <2 x double> [[X2]], i8 [[X3]])
+; CHECK-NEXT: [[TMP11:%.*]] = icmp ne <2 x i64> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP12:%.*]] = sext <2 x i1> [[TMP11]] to <2 x i64>
+; CHECK-NEXT: [[TMP13:%.*]] = select <2 x i1> splat (i1 true), <2 x i64> [[TMP12]], <2 x i64> [[TMP2]]
; CHECK-NEXT: [[RES1:%.*]] = call <2 x double> @llvm.x86.avx512.mask.rndscale.pd.128(<2 x double> [[X0]], i32 88, <2 x double> [[X2]], i8 -1)
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <2 x i64> [[TMP8]], [[TMP13]]
; CHECK-NEXT: [[RES2:%.*]] = fadd <2 x double> [[RES]], [[RES1]]
-; CHECK-NEXT: store <2 x i64> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <2 x i64> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <2 x double> [[RES2]]
;
%res = call <2 x double> @llvm.x86.avx512.mask.rndscale.pd.128(<2 x double> %x0, i32 4, <2 x double> %x2, i8 %x3)
@@ -7171,36 +7162,29 @@ define <4 x double>@test_int_x86_avx512_mask_rndscale_pd_256(<4 x double> %x0, <
;
; CHECK-LABEL: define <4 x double> @test_int_x86_avx512_mask_rndscale_pd_256(
; CHECK-SAME: <4 x double> [[X0:%.*]], <4 x double> [[X2:%.*]], i8 [[X3:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 64) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i64>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i64>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 32) to ptr), align 8
-; CHECK-NEXT: [[TMP3:%.*]] = 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: [[TMP4:%.*]] = bitcast <4 x i64> [[TMP1]] to i256
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i256 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <4 x i64> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i256 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[X3]] to i4
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast i4 [[TMP4]] to <4 x i1>
+; CHECK-NEXT: [[TMP6:%.*]] = icmp ne <4 x i64> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP7:%.*]] = sext <4 x i1> [[TMP6]] to <4 x i64>
+; CHECK-NEXT: [[TMP8:%.*]] = select <4 x i1> [[TMP5]], <4 x i64> [[TMP7]], <4 x i64> [[TMP2]]
; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR3:%.*]] = or i1 [[_MSOR]], [[_MSCMP2]]
-; CHECK-NEXT: br i1 [[_MSOR3]], label %[[BB6:.*]], label %[[BB7:.*]], !prof [[PROF1]]
-; CHECK: [[BB6]]:
+; CHECK-NEXT: br i1 [[_MSCMP2]], label %[[BB9:.*]], label %[[BB10:.*]], !prof [[PROF1]]
+; CHECK: [[BB9]]:
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR6]]
; CHECK-NEXT: unreachable
-; CHECK: [[BB7]]:
-; CHECK-NEXT: [[RES:%.*]] = call <4 x double> @llvm.x86.avx512.mask.rndscale.pd.256(<4 x double> [[X0]], i32 4, <4 x double> [[X2]], i8 [[X3]])
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <4 x i64> [[TMP1]] to i256
-; CHECK-NEXT: [[_MSCMP4:%.*]] = icmp ne i256 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <4 x i64> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i256 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSCMP4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label %[[BB10:.*]], label %[[BB11:.*]], !prof [[PROF1]]
; CHECK: [[BB10]]:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR6]]
-; CHECK-NEXT: unreachable
-; CHECK: [[BB11]]:
+; CHECK-NEXT: [[RES:%.*]] = call <4 x double> @llvm.x86.avx512.mask.rndscale.pd.256(<4 x double> [[X0]], i32 4, <4 x double> [[X2]], i8 [[X3]])
+; CHECK-NEXT: [[TMP11:%.*]] = icmp ne <4 x i64> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP12:%.*]] = sext <4 x i1> [[TMP11]] to <4 x i64>
+; CHECK-NEXT: [[TMP13:%.*]] = select <4 x i1> splat (i1 true), <4 x i64> [[TMP12]], <4 x i64> [[TMP2]]
; CHECK-NEXT: [[RES1:%.*]] = call <4 x double> @llvm.x86.avx512.mask.rndscale.pd.256(<4 x double> [[X0]], i32 88, <4 x double> [[X2]], i8 -1)
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <4 x i64> [[TMP8]], [[TMP13]]
; CHECK-NEXT: [[RES2:%.*]] = fadd <4 x double> [[RES]], [[RES1]]
-; CHECK-NEXT: store <4 x i64> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <4 x i64> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <4 x double> [[RES2]]
;
%res = call <4 x double> @llvm.x86.avx512.mask.rndscale.pd.256(<4 x double> %x0, i32 4, <4 x double> %x2, i8 %x3)
@@ -7215,36 +7199,29 @@ define <4 x float>@test_int_x86_avx512_mask_rndscale_ps_128(<4 x float> %x0, <4
;
; CHECK-LABEL: define <4 x float> @test_int_x86_avx512_mask_rndscale_ps_128(
; CHECK-SAME: <4 x float> [[X0:%.*]], <4 x float> [[X2:%.*]], i8 [[X3:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 32) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 16) to ptr), align 8
-; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 32) to ptr), align 8
; CHECK-NEXT: call void @llvm.donothing()
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <4 x i32> [[TMP1]] to i128
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i128 [[TMP4]], 0
-; CHECK-NEXT: [[TMP5:%.*]] = bitcast <4 x i32> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i128 [[TMP5]], 0
-; CHECK-NEXT: [[_MSOR:%.*]] = or i1 [[_MSCMP]], [[_MSCMP1]]
+; CHECK-NEXT: [[TMP4:%.*]] = trunc i8 [[X3]] to i4
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast i4 [[TMP4]] to <4 x i1>
+; CHECK-NEXT: [[TMP6:%.*]] = icmp ne <4 x i32> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP7:%.*]] = sext <4 x i1> [[TMP6]] to <4 x i32>
+; CHECK-NEXT: [[TMP8:%.*]] = select <4 x i1> [[TMP5]], <4 x i32> [[TMP7]], <4 x i32> [[TMP2]]
; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR3:%.*]] = or i1 [[_MSOR]], [[_MSCMP2]]
-; CHECK-NEXT: br i1 [[_MSOR3]], label %[[BB6:.*]], label %[[BB7:.*]], !prof [[PROF1]]
-; CHECK: [[BB6]]:
+; CHECK-NEXT: br i1 [[_MSCMP2]], label %[[BB9:.*]], label %[[BB10:.*]], !prof [[PROF1]]
+; CHECK: [[BB9]]:
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR6]]
; CHECK-NEXT: unreachable
-; CHECK: [[BB7]]:
-; CHECK-NEXT: [[RES:%.*]] = call <4 x float> @llvm.x86.avx512.mask.rndscale.ps.128(<4 x float> [[X0]], i32 88, <4 x float> [[X2]], i8 [[X3]])
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <4 x i32> [[TMP1]] to i128
-; CHECK-NEXT: [[_MSCMP4:%.*]] = icmp ne i128 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <4 x i32> [[TMP2]] to i128
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i128 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSCMP4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label %[[BB10:.*]], label %[[BB11:.*]], !prof [[PROF1]]
; CHECK: [[BB10]]:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR6]]
-; CHECK-NEXT: unreachable
-; CHECK: [[BB11]]:
+; CHECK-NEXT: [[RES:%.*]] = call <4 x float> @llvm.x86.avx512.mask.rndscale.ps.128(<4 x float> [[X0]], i32 88, <4 x float> [[X2]], i8 [[X3]])
+; CHECK-NEXT: [[TMP11:%.*]] = icmp ne <4 x i32> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP12:%.*]] = sext <4 x i1> [[TMP11]] to <4 x i32>
+; CHECK-NEXT: [[TMP13:%.*]] = select <4 x i1> splat (i1 true), <4 x i32> [[TMP12]], <4 x i32> [[TMP2]]
; CHECK-NEXT: [[RES1:%.*]] = call <4 x float> @llvm.x86.avx512.mask.rndscale.ps.128(<4 x float> [[X0]], i32 4, <4 x float> [[X2]], i8 -1)
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <4 x i32> [[TMP8]], [[TMP13]]
; CHECK-NEXT: [[RES2:%.*]] = fadd <4 x float> [[RES]], [[RES1]]
-; CHECK-NEXT: store <4 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <4 x i32> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <4 x float> [[RES2]]
;
%res = call <4 x float> @llvm.x86.avx512.mask.rndscale.ps.128(<4 x float> %x0, i32 88, <4 x float> %x2, i8 %x3)
@@ -7259,36 +7236,28 @@ define <8 x float>@test_int_x86_avx512_mask_rndscale_ps_256(<8 x float> %x0, <8
;
; CHECK-LABEL: define <8 x float> @test_int_x86_avx512_mask_rndscale_ps_256(
; CHECK-SAME: <8 x float> [[X0:%.*]], <8 x float> [[X2:%.*]], i8 [[X3:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP3:%.*]] = 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 i32>, 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 32) to ptr), align 8
-; CHECK-NEXT: [[TMP3:%.*]] = 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: [[TMP4:%.*]] = bitcast <8 x i32> [[TMP1]] to i256
-; CHECK-NEXT: [[_MSCMP:%.*]] = icmp ne i256 [[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: [[TMP4:%.*]] = bitcast i8 [[X3]] to <8 x i1>
+; CHECK-NEXT: [[TMP5:%.*]] = icmp ne <8 x i32> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP6:%.*]] = sext <8 x i1> [[TMP5]] to <8 x i32>
+; CHECK-NEXT: [[TMP7:%.*]] = select <8 x i1> [[TMP4]], <8 x i32> [[TMP6]], <8 x i32> [[TMP2]]
; CHECK-NEXT: [[_MSCMP2:%.*]] = icmp ne i8 [[TMP3]], 0
-; CHECK-NEXT: [[_MSOR3:%.*]] = or i1 [[_MSOR]], [[_MSCMP2]]
-; CHECK-NEXT: br i1 [[_MSOR3]], label %[[BB6:.*]], label %[[BB7:.*]], !prof [[PROF1]]
-; CHECK: [[BB6]]:
+; CHECK-NEXT: br i1 [[_MSCMP2]], label %[[BB8:.*]], label %[[BB9:.*]], !prof [[PROF1]]
+; CHECK: [[BB8]]:
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR6]]
; CHECK-NEXT: unreachable
-; CHECK: [[BB7]]:
+; CHECK: [[BB9]]:
; CHECK-NEXT: [[RES:%.*]] = call <8 x float> @llvm.x86.avx512.mask.rndscale.ps.256(<8 x float> [[X0]], i32 5, <8 x float> [[X2]], i8 [[X3]])
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i32> [[TMP1]] to i256
-; CHECK-NEXT: [[_MSCMP4:%.*]] = icmp ne i256 [[TMP8]], 0
-; CHECK-NEXT: [[TMP9:%.*]] = bitcast <8 x i32> [[TMP2]] to i256
-; CHECK-NEXT: [[_MSCMP5:%.*]] = icmp ne i256 [[TMP9]], 0
-; CHECK-NEXT: [[_MSOR6:%.*]] = or i1 [[_MSCMP4]], [[_MSCMP5]]
-; CHECK-NEXT: br i1 [[_MSOR6]], label %[[BB10:.*]], label %[[BB11:.*]], !prof [[PROF1]]
-; CHECK: [[BB10]]:
-; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR6]]
-; CHECK-NEXT: unreachable
-; CHECK: [[BB11]]:
+; CHECK-NEXT: [[TMP10:%.*]] = icmp ne <8 x i32> [[TMP1]], zeroinitializer
+; CHECK-NEXT: [[TMP11:%.*]] = sext <8 x i1> [[TMP10]] to <8 x i32>
+; CHECK-NEXT: [[TMP12:%.*]] = select <8 x i1> splat (i1 true), <8 x i32> [[TMP11]], <8 x i32> [[TMP2]]
; CHECK-NEXT: [[RES1:%.*]] = call <8 x float> @llvm.x86.avx512.mask.rndscale.ps.256(<8 x float> [[X0]], i32 66, <8 x float> [[X2]], i8 -1)
+; CHECK-NEXT: [[_MSPROP:%.*]] = or <8 x i32> [[TMP7]], [[TMP12]]
; CHECK-NEXT: [[RES2:%.*]] = fadd <8 x float> [[RES]], [[RES1]]
-; CHECK-NEXT: store <8 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT: store <8 x i32> [[_MSPROP]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x float> [[RES2]]
;
%res = call <8 x float> @llvm.x86.avx512.mask.rndscale.ps.256(<8 x float> %x0, i32 5, <8 x float> %x2, i8 %x3)
More information about the llvm-commits
mailing list