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
; Test the NVVM reflect pass functionality: verifying that reflect calls are replaced with
|
|
; appropriate values based on command-line options. Verify that we can handle custom reflect arguments
|
|
; that aren't __CUDA_ARCH or __CUDA_FTZ. If that argument is given a value on the command-line,
|
|
; the reflect call should be replaced with that value. Otherwise, the reflect call should be replaced with 0.
|
|
|
|
; RUN: opt -passes=nvvm-reflect -mtriple=nvptx-nvidia-cuda \
|
|
; RUN: -nvvm-reflect-add __CUDA_FTZ=1 -nvvm-reflect-add __CUDA_ARCH=350 %s -S \
|
|
; RUN: | FileCheck %s --check-prefixes=COMMON,FTZ1,ARCH350,CUSTOM-ABSENT
|
|
; RUN: opt -passes=nvvm-reflect -mtriple=nvptx-nvidia-cuda \
|
|
; RUN: -nvvm-reflect-add __CUDA_FTZ=0 -nvvm-reflect-add __CUDA_ARCH=520 %s -S \
|
|
; RUN: | FileCheck %s --check-prefixes=COMMON,FTZ0,ARCH520,CUSTOM-ABSENT
|
|
; RUN: opt -passes=nvvm-reflect -mtriple=nvptx-nvidia-cuda \
|
|
; RUN: -nvvm-reflect-add __CUDA_FTZ=0 -nvvm-reflect-add __CUDA_ARCH=520 \
|
|
; RUN: -nvvm-reflect-add __CUSTOM_VALUE=42 %s -S \
|
|
; RUN: | FileCheck %s --check-prefixes=COMMON,CUSTOM-PRESENT
|
|
|
|
; To ensure that command line options override module options, create a copy of this test file
|
|
; with module options appended and rerun some tests.
|
|
|
|
; RUN: cat %s > %t.options
|
|
; RUN: echo '!llvm.module.flags = !{!0}' >> %t.options
|
|
; RUN: echo '!0 = !{i32 4, !"nvvm-reflect-ftz", i32 1}' >> %t.options
|
|
; RUN: opt -passes=nvvm-reflect -mtriple=nvptx-nvidia-cuda \
|
|
; RUN: -nvvm-reflect-add __CUDA_FTZ=0 -nvvm-reflect-add __CUDA_ARCH=520 %t.options -S \
|
|
; RUN: | FileCheck %s --check-prefixes=COMMON,FTZ0,ARCH520
|
|
|
|
declare i32 @__nvvm_reflect(ptr)
|
|
@ftz = private unnamed_addr addrspace(1) constant [11 x i8] c"__CUDA_FTZ\00"
|
|
@arch = private unnamed_addr addrspace(1) constant [12 x i8] c"__CUDA_ARCH\00"
|
|
@custom = private unnamed_addr addrspace(1) constant [15 x i8] c"__CUSTOM_VALUE\00"
|
|
|
|
; COMMON-LABEL: define i32 @test_ftz()
|
|
; FTZ1: ret i32 1
|
|
; FTZ0: ret i32 0
|
|
define i32 @test_ftz() {
|
|
%1 = call i32 @__nvvm_reflect(ptr addrspacecast (ptr addrspace(1) @ftz to ptr))
|
|
ret i32 %1
|
|
}
|
|
|
|
; COMMON-LABEL: define i32 @test_arch()
|
|
; ARCH350: ret i32 350
|
|
; ARCH520: ret i32 520
|
|
define i32 @test_arch() {
|
|
%1 = call i32 @__nvvm_reflect(ptr addrspacecast (ptr addrspace(1) @arch to ptr))
|
|
ret i32 %1
|
|
}
|
|
|
|
; COMMON-LABEL: define i32 @test_custom()
|
|
; CUSTOM-ABSENT: ret i32 0
|
|
; CUSTOM-PRESENT: ret i32 42
|
|
define i32 @test_custom() {
|
|
%1 = call i32 @__nvvm_reflect(ptr addrspacecast (ptr addrspace(1) @custom to ptr))
|
|
ret i32 %1
|
|
}
|