[msan] Add support for avx_round_pd_256/avx_round_ps_256

[alexander-shaposhnikov]

This is a follow-up to #118441

p.s. perhaps, there might be more similar cases.

[llvmbot]

@llvm/pr-subscribers-llvm-transforms

@llvm/pr-subscribers-compiler-rt-sanitizer

Author: Alexander Shaposhnikov (alexander-shaposhnikov)

Changes

This is a follow-up to #118441

p.s. perhaps, there might be more similar cases.

---

Full diff: https://github.com/llvm/llvm-project/pull/119334.diff

3 Files Affected:

• (modified) llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp (+2)
• (modified) llvm/test/Instrumentation/MemorySanitizer/X86/avx-intrinsics-x86.ll (+2-16)
• (modified) llvm/test/Instrumentation/MemorySanitizer/i386/avx-intrinsics-i386.ll (+2-16)

diff --git a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
index 6853b71b132805..429e323b6b7c24 100644
--- a/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp
@@ -4346,6 +4346,8 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
       handlePclmulIntrinsic(I);
       break;
 
+    case Intrinsic::x86_avx_round_pd_256:
+    case Intrinsic::x86_avx_round_ps_256:
     case Intrinsic::x86_sse41_round_pd:
     case Intrinsic::x86_sse41_round_ps:
       handleRoundPdPsIntrinsic(I);
diff --git a/llvm/test/Instrumentation/MemorySanitizer/X86/avx-intrinsics-x86.ll b/llvm/test/Instrumentation/MemorySanitizer/X86/avx-intrinsics-x86.ll
index 5bb2c3f0e233b9..48ecd53b40c72a 100644
--- a/llvm/test/Instrumentation/MemorySanitizer/X86/avx-intrinsics-x86.ll
+++ b/llvm/test/Instrumentation/MemorySanitizer/X86/avx-intrinsics-x86.ll
@@ -903,15 +903,8 @@ define <4 x double> @test_x86_avx_round_pd_256(<4 x double> %a0) #0 {
 ; CHECK-LABEL: @test_x86_avx_round_pd_256(
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i64>, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x i64> [[TMP1]] to i256
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i256 [[TMP2]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label [[TMP3:%.*]], label [[TMP4:%.*]], !prof [[PROF1]]
-; CHECK:       3:
-; CHECK-NEXT:    call void @__msan_warning_noreturn()
-; CHECK-NEXT:    unreachable
-; CHECK:       4:
 ; CHECK-NEXT:    [[RES:%.*]] = call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> [[A0:%.*]], i32 7)
-; CHECK-NEXT:    store <4 x i64> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT:    store <4 x i64> [[TMP1]], ptr @__msan_retval_tls, align 8
 ; CHECK-NEXT:    ret <4 x double> [[RES]]
 ;
   %res = call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> %a0, i32 7) ; <<4 x double>> [#uses=1]
@@ -924,15 +917,8 @@ define <8 x float> @test_x86_avx_round_ps_256(<8 x float> %a0) #0 {
 ; CHECK-LABEL: @test_x86_avx_round_ps_256(
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <8 x i32>, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x i32> [[TMP1]] to i256
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i256 [[TMP2]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label [[TMP3:%.*]], label [[TMP4:%.*]], !prof [[PROF1]]
-; CHECK:       3:
-; CHECK-NEXT:    call void @__msan_warning_noreturn()
-; CHECK-NEXT:    unreachable
-; CHECK:       4:
 ; CHECK-NEXT:    [[RES:%.*]] = call <8 x float> @llvm.x86.avx.round.ps.256(<8 x float> [[A0:%.*]], i32 7)
-; CHECK-NEXT:    store <8 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT:    store <8 x i32> [[TMP1]], ptr @__msan_retval_tls, align 8
 ; CHECK-NEXT:    ret <8 x float> [[RES]]
 ;
   %res = call <8 x float> @llvm.x86.avx.round.ps.256(<8 x float> %a0, i32 7) ; <<8 x float>> [#uses=1]
diff --git a/llvm/test/Instrumentation/MemorySanitizer/i386/avx-intrinsics-i386.ll b/llvm/test/Instrumentation/MemorySanitizer/i386/avx-intrinsics-i386.ll
index bd3b9388eadff7..3ac0fa2415a0f4 100644
--- a/llvm/test/Instrumentation/MemorySanitizer/i386/avx-intrinsics-i386.ll
+++ b/llvm/test/Instrumentation/MemorySanitizer/i386/avx-intrinsics-i386.ll
@@ -940,15 +940,8 @@ define <4 x double> @test_x86_avx_round_pd_256(<4 x double> %a0) #0 {
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i64>, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    [[TMP4:%.*]] = load i64, ptr @__msan_va_arg_overflow_size_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x i64> [[TMP1]] to i256
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i256 [[TMP2]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label [[TMP6:%.*]], label [[TMP5:%.*]], !prof [[PROF1]]
-; CHECK:       4:
-; CHECK-NEXT:    call void @__msan_warning_noreturn()
-; CHECK-NEXT:    unreachable
-; CHECK:       5:
 ; CHECK-NEXT:    [[RES:%.*]] = call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> [[A0:%.*]], i32 7)
-; CHECK-NEXT:    store <4 x i64> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT:    store <4 x i64> [[TMP1]], ptr @__msan_retval_tls, align 8
 ; CHECK-NEXT:    ret <4 x double> [[RES]]
 ;
   %res = call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> %a0, i32 7) ; <<4 x double>> [#uses=1]
@@ -962,15 +955,8 @@ define <8 x float> @test_x86_avx_round_ps_256(<8 x float> %a0) #0 {
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <8 x i32>, ptr @__msan_param_tls, align 8
 ; CHECK-NEXT:    [[TMP4:%.*]] = load i64, ptr @__msan_va_arg_overflow_size_tls, align 8
 ; CHECK-NEXT:    call void @llvm.donothing()
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast <8 x i32> [[TMP1]] to i256
-; CHECK-NEXT:    [[_MSCMP:%.*]] = icmp ne i256 [[TMP2]], 0
-; CHECK-NEXT:    br i1 [[_MSCMP]], label [[TMP6:%.*]], label [[TMP5:%.*]], !prof [[PROF1]]
-; CHECK:       4:
-; CHECK-NEXT:    call void @__msan_warning_noreturn()
-; CHECK-NEXT:    unreachable
-; CHECK:       5:
 ; CHECK-NEXT:    [[RES:%.*]] = call <8 x float> @llvm.x86.avx.round.ps.256(<8 x float> [[A0:%.*]], i32 7)
-; CHECK-NEXT:    store <8 x i32> zeroinitializer, ptr @__msan_retval_tls, align 8
+; CHECK-NEXT:    store <8 x i32> [[TMP1]], ptr @__msan_retval_tls, align 8
 ; CHECK-NEXT:    ret <8 x float> [[RES]]
 ;
   %res = call <8 x float> @llvm.x86.avx.round.ps.256(<8 x float> %a0, i32 7) ; <<8 x float>> [#uses=1]