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
37 lines
1.2 KiB
LLVM
37 lines
1.2 KiB
LLVM
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}
|
|
|
|
target triple = "nvptx-nvidia-cuda"
|
|
|
|
; Function Attrs: nounwind
|
|
; CHECK: .entry foo
|
|
define ptx_kernel void @foo(ptr nocapture %a) #0 {
|
|
%val = load float, ptr %a
|
|
%tan = tail call fastcc float @__nv_fast_tanf(float %val)
|
|
store float %tan, ptr %a
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare float @llvm.nvvm.sin.approx.ftz.f(float) #1
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare float @llvm.nvvm.cos.approx.ftz.f(float) #1
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare float @llvm.nvvm.div.approx.ftz.f(float, float) #1
|
|
|
|
; Function Attrs: alwaysinline inlinehint nounwind readnone
|
|
; CHECK: .func (.param .b32 func_retval0) __nv_fast_tanf
|
|
define internal fastcc float @__nv_fast_tanf(float %a) #2 {
|
|
entry:
|
|
%0 = tail call float @llvm.nvvm.sin.approx.ftz.f(float %a)
|
|
%1 = tail call float @llvm.nvvm.cos.approx.ftz.f(float %a)
|
|
%2 = tail call float @llvm.nvvm.div.approx.ftz.f(float %0, float %1)
|
|
ret float %2
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone }
|
|
attributes #2 = { alwaysinline inlinehint nounwind readnone }
|