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
55 lines
2.5 KiB
LLVM
55 lines
2.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt < %s -passes=instsimplify -march=nvptx64 --mcpu=sm_86 --mattr=+ptx72 -S | FileCheck %s --check-prefixes CHECK,FOLDING_ENABLED
|
|
; RUN: opt < %s -disable-fp-call-folding -passes=instsimplify -march=nvptx64 --mcpu=sm_86 --mattr=+ptx72 -S | FileCheck %s --check-prefixes CHECK,FOLDING_DISABLED
|
|
|
|
; Check that we can disable folding of intrinsic calls via both the -disable-fp-call-folding flag and the strictfp attribute.
|
|
|
|
; Should be folded by default unless -disable-fp-call-folding is set
|
|
define float @test_fmax_ftz_nan_xorsign_abs_f() {
|
|
; FOLDING_ENABLED-LABEL: define float @test_fmax_ftz_nan_xorsign_abs_f() {
|
|
; FOLDING_ENABLED-NEXT: ret float -2.000000e+00
|
|
;
|
|
; FOLDING_DISABLED-LABEL: define float @test_fmax_ftz_nan_xorsign_abs_f() {
|
|
; FOLDING_DISABLED-NEXT: [[RES:%.*]] = call float @llvm.nvvm.fmax.ftz.nan.xorsign.abs.f(float 1.250000e+00, float -2.000000e+00)
|
|
; FOLDING_DISABLED-NEXT: ret float [[RES]]
|
|
;
|
|
%res = call float @llvm.nvvm.fmax.ftz.nan.xorsign.abs.f(float 1.25, float -2.0)
|
|
ret float %res
|
|
}
|
|
|
|
; Check that -disable-fp-call-folding triggers for LLVM instrincis, not just NVPTX target-specific ones.
|
|
define float @test_llvm_sin() {
|
|
; FOLDING_ENABLED-LABEL: define float @test_llvm_sin() {
|
|
; FOLDING_ENABLED-NEXT: ret float f0x3EF57744
|
|
;
|
|
; FOLDING_DISABLED-LABEL: define float @test_llvm_sin() {
|
|
; FOLDING_DISABLED-NEXT: [[RES:%.*]] = call float @llvm.sin.f32(float 5.000000e-01)
|
|
; FOLDING_DISABLED-NEXT: ret float [[RES]]
|
|
;
|
|
%res = call float @llvm.sin.f32(float 0.5)
|
|
ret float %res
|
|
}
|
|
|
|
; Should not be folded, even when -disable-fp-call-folding is not set, as it is marked as strictfp.
|
|
define float @test_fmax_ftz_nan_f_strictfp() {
|
|
; CHECK-LABEL: define float @test_fmax_ftz_nan_f_strictfp() {
|
|
; CHECK-NEXT: [[RES:%.*]] = call float @llvm.nvvm.fmax.ftz.nan.f(float 1.250000e+00, float -2.000000e+00) #[[ATTR1:[0-9]+]]
|
|
; CHECK-NEXT: ret float [[RES]]
|
|
;
|
|
%res = call float @llvm.nvvm.fmax.ftz.nan.f(float 1.25, float -2.0) #1
|
|
ret float %res
|
|
}
|
|
|
|
; Check that strictfp disables folding for LLVM math intrinsics like sin.f32
|
|
; even when -disable-fp-call-folding is not set.
|
|
define float @test_llvm_sin_strictfp() {
|
|
; CHECK-LABEL: define float @test_llvm_sin_strictfp() {
|
|
; CHECK-NEXT: [[RES:%.*]] = call float @llvm.sin.f32(float 5.000000e-01) #[[ATTR1]]
|
|
; CHECK-NEXT: ret float [[RES]]
|
|
;
|
|
%res = call float @llvm.sin.f32(float 0.5) #1
|
|
ret float %res
|
|
}
|
|
|
|
attributes #1 = { strictfp }
|