derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
184 lines
9.9 KiB
LLVM
184 lines
9.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt < %s -passes=msan -S | FileCheck %s
|
|
;
|
|
; Forked from llvm/test/CodeGen/X86/f16c-intrinsics.ll
|
|
;
|
|
; Handled by handleSSEVectorConvertIntrinsicByProp:
|
|
; - llvm.x86.vcvtps2ph.128/256
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
define <8 x i16> @test_x86_vcvtps2ph_128(<4 x float> %a0) #0 {
|
|
; CHECK-LABEL: define <8 x i16> @test_x86_vcvtps2ph_128(
|
|
; CHECK-SAME: <4 x float> [[A0:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, ptr @__msan_param_tls, align 8
|
|
; CHECK-NEXT: call void @llvm.donothing()
|
|
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <4 x i32> [[TMP1]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP3:%.*]] = sext <4 x i1> [[TMP2]] to <4 x i16>
|
|
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <4 x i16> [[TMP3]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: [[RES:%.*]] = call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[A0]], i32 0)
|
|
; CHECK-NEXT: store <8 x i16> [[TMP11]], ptr @__msan_retval_tls, align 8
|
|
; CHECK-NEXT: ret <8 x i16> [[RES]]
|
|
;
|
|
%res = call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float>, i32) nounwind readonly
|
|
|
|
define <8 x i16> @test_x86_vcvtps2ph_256(<8 x float> %a0) #0 {
|
|
; CHECK-LABEL: define <8 x i16> @test_x86_vcvtps2ph_256(
|
|
; CHECK-SAME: <8 x float> [[A0:%.*]]) #[[ATTR0]] {
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i32>, ptr @__msan_param_tls, align 8
|
|
; CHECK-NEXT: call void @llvm.donothing()
|
|
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <8 x i32> [[TMP1]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP3:%.*]] = sext <8 x i1> [[TMP2]] to <8 x i16>
|
|
; CHECK-NEXT: [[RES:%.*]] = call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> [[A0]], i32 0)
|
|
; CHECK-NEXT: store <8 x i16> [[TMP3]], ptr @__msan_retval_tls, align 8
|
|
; CHECK-NEXT: ret <8 x i16> [[RES]]
|
|
;
|
|
%res = call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float>, i32) nounwind readonly
|
|
|
|
|
|
define void @test_x86_vcvtps2ph_256_m(ptr nocapture %d, <8 x float> %a) nounwind #0 {
|
|
; CHECK-LABEL: define void @test_x86_vcvtps2ph_256_m(
|
|
; CHECK-SAME: ptr captures(none) [[D:%.*]], <8 x float> [[A:%.*]]) #[[ATTR2:[0-9]+]] {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[TMP17:%.*]] = load <8 x i32>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 8), align 8
|
|
; CHECK-NEXT: [[TMP18:%.*]] = load i64, ptr @__msan_param_tls, align 8
|
|
; CHECK-NEXT: call void @llvm.donothing()
|
|
; CHECK-NEXT: [[TMP20:%.*]] = icmp ne <8 x i32> [[TMP17]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP21:%.*]] = sext <8 x i1> [[TMP20]] to <8 x i16>
|
|
; CHECK-NEXT: [[TMP0:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> [[A]], i32 3)
|
|
; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i64 [[TMP18]], 0
|
|
; CHECK-NEXT: br i1 [[_MSCMP1]], label %[[BB5:.*]], label %[[BB6:.*]], !prof [[PROF1:![0-9]+]]
|
|
; CHECK: [[BB5]]:
|
|
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR4:[0-9]+]]
|
|
; CHECK-NEXT: unreachable
|
|
; CHECK: [[BB6]]:
|
|
; CHECK-NEXT: [[TMP1:%.*]] = ptrtoint ptr [[D]] to i64
|
|
; CHECK-NEXT: [[TMP2:%.*]] = xor i64 [[TMP1]], 87960930222080
|
|
; CHECK-NEXT: [[TMP3:%.*]] = inttoptr i64 [[TMP2]] to ptr
|
|
; CHECK-NEXT: store <8 x i16> [[TMP21]], ptr [[TMP3]], align 16
|
|
; CHECK-NEXT: store <8 x i16> [[TMP0]], ptr [[D]], align 16
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a, i32 3)
|
|
store <8 x i16> %0, ptr %d, align 16
|
|
ret void
|
|
}
|
|
|
|
define void @test_x86_vcvtps2ph_128_m(ptr nocapture %d, <4 x float> %a) nounwind #0 {
|
|
; CHECK-LABEL: define void @test_x86_vcvtps2ph_128_m(
|
|
; CHECK-SAME: ptr captures(none) [[D:%.*]], <4 x float> [[A:%.*]]) #[[ATTR2]] {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[TMP9:%.*]] = load <4 x i32>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 8), align 8
|
|
; CHECK-NEXT: [[TMP10:%.*]] = load i64, ptr @__msan_param_tls, align 8
|
|
; CHECK-NEXT: call void @llvm.donothing()
|
|
; CHECK-NEXT: [[TMP12:%.*]] = icmp ne <4 x i32> [[TMP9]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP13:%.*]] = sext <4 x i1> [[TMP12]] to <4 x i16>
|
|
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <4 x i16> [[TMP13]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: [[TMP0:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[A]], i32 3)
|
|
; CHECK-NEXT: [[_MSPROP:%.*]] = shufflevector <8 x i16> [[TMP11]], <8 x i16> splat (i16 -1), <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i16> [[TMP0]], <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i64 [[TMP10]], 0
|
|
; CHECK-NEXT: br i1 [[_MSCMP1]], label %[[BB7:.*]], label %[[BB8:.*]], !prof [[PROF1]]
|
|
; CHECK: [[BB7]]:
|
|
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR4]]
|
|
; CHECK-NEXT: unreachable
|
|
; CHECK: [[BB8]]:
|
|
; CHECK-NEXT: [[TMP2:%.*]] = ptrtoint ptr [[D]] to i64
|
|
; CHECK-NEXT: [[TMP3:%.*]] = xor i64 [[TMP2]], 87960930222080
|
|
; CHECK-NEXT: [[TMP4:%.*]] = inttoptr i64 [[TMP3]] to ptr
|
|
; CHECK-NEXT: store <4 x i16> [[_MSPROP]], ptr [[TMP4]], align 8
|
|
; CHECK-NEXT: store <4 x i16> [[TMP1]], ptr [[D]], align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a, i32 3)
|
|
%1 = shufflevector <8 x i16> %0, <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
store <4 x i16> %1, ptr %d, align 8
|
|
ret void
|
|
}
|
|
|
|
define void @test_x86_vcvtps2ph_128_m2(ptr nocapture %hf4x16, <4 x float> %f4X86) #0 {
|
|
; CHECK-LABEL: define void @test_x86_vcvtps2ph_128_m2(
|
|
; CHECK-SAME: ptr captures(none) [[HF4X16:%.*]], <4 x float> [[F4X86:%.*]]) #[[ATTR0]] {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load <4 x i32>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 8), align 8
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load i64, ptr @__msan_param_tls, align 8
|
|
; CHECK-NEXT: call void @llvm.donothing()
|
|
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <4 x i32> [[TMP0]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP3:%.*]] = sext <4 x i1> [[TMP2]] to <4 x i16>
|
|
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <4 x i16> [[TMP3]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: [[TMP11:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[F4X86]], i32 3)
|
|
; CHECK-NEXT: [[TMP13:%.*]] = bitcast <8 x i16> [[TMP14]] to <2 x i64>
|
|
; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i16> [[TMP11]] to <2 x double>
|
|
; CHECK-NEXT: [[_MSPROP:%.*]] = extractelement <2 x i64> [[TMP13]], i32 0
|
|
; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <2 x double> [[TMP12]], i32 0
|
|
; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i64 [[TMP1]], 0
|
|
; CHECK-NEXT: br i1 [[_MSCMP1]], label %[[BB8:.*]], label %[[BB9:.*]], !prof [[PROF1]]
|
|
; CHECK: [[BB8]]:
|
|
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR4]]
|
|
; CHECK-NEXT: unreachable
|
|
; CHECK: [[BB9]]:
|
|
; CHECK-NEXT: [[TMP15:%.*]] = ptrtoint ptr [[HF4X16]] to i64
|
|
; CHECK-NEXT: [[TMP16:%.*]] = xor i64 [[TMP15]], 87960930222080
|
|
; CHECK-NEXT: [[TMP17:%.*]] = inttoptr i64 [[TMP16]] to ptr
|
|
; CHECK-NEXT: store i64 [[_MSPROP]], ptr [[TMP17]], align 8
|
|
; CHECK-NEXT: store double [[VECEXT]], ptr [[HF4X16]], align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %f4X86, i32 3)
|
|
%1 = bitcast <8 x i16> %0 to <2 x double>
|
|
%vecext = extractelement <2 x double> %1, i32 0
|
|
store double %vecext, ptr %hf4x16, align 8
|
|
ret void
|
|
}
|
|
|
|
define void @test_x86_vcvtps2ph_128_m3(ptr nocapture %hf4x16, <4 x float> %f4X86) #0 {
|
|
; CHECK-LABEL: define void @test_x86_vcvtps2ph_128_m3(
|
|
; CHECK-SAME: ptr captures(none) [[HF4X16:%.*]], <4 x float> [[F4X86:%.*]]) #[[ATTR0]] {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load <4 x i32>, ptr getelementptr (i8, ptr @__msan_param_tls, i64 8), align 8
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load i64, ptr @__msan_param_tls, align 8
|
|
; CHECK-NEXT: call void @llvm.donothing()
|
|
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <4 x i32> [[TMP0]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP3:%.*]] = sext <4 x i1> [[TMP2]] to <4 x i16>
|
|
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <4 x i16> [[TMP3]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: [[TMP11:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[F4X86]], i32 3)
|
|
; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i16> [[TMP13]] to <2 x i64>
|
|
; CHECK-NEXT: [[TMP14:%.*]] = bitcast <8 x i16> [[TMP11]] to <2 x i64>
|
|
; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <2 x i64> [[TMP12]], i32 0
|
|
; CHECK-NEXT: [[VECEXT1:%.*]] = extractelement <2 x i64> [[TMP14]], i32 0
|
|
; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i64 [[TMP1]], 0
|
|
; CHECK-NEXT: br i1 [[_MSCMP1]], label %[[BB8:.*]], label %[[BB9:.*]], !prof [[PROF1]]
|
|
; CHECK: [[BB8]]:
|
|
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR4]]
|
|
; CHECK-NEXT: unreachable
|
|
; CHECK: [[BB9]]:
|
|
; CHECK-NEXT: [[TMP15:%.*]] = ptrtoint ptr [[HF4X16]] to i64
|
|
; CHECK-NEXT: [[TMP16:%.*]] = xor i64 [[TMP15]], 87960930222080
|
|
; CHECK-NEXT: [[TMP17:%.*]] = inttoptr i64 [[TMP16]] to ptr
|
|
; CHECK-NEXT: store i64 [[VECEXT]], ptr [[TMP17]], align 8
|
|
; CHECK-NEXT: store i64 [[VECEXT1]], ptr [[HF4X16]], align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %f4X86, i32 3)
|
|
%1 = bitcast <8 x i16> %0 to <2 x i64>
|
|
%vecext = extractelement <2 x i64> %1, i32 0
|
|
store i64 %vecext, ptr %hf4x16, align 8
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { sanitize_memory }
|
|
;.
|
|
; CHECK: [[PROF1]] = !{!"branch_weights", i32 1, i32 1048575}
|
|
;.
|