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
76 lines
2.6 KiB
LLVM
76 lines
2.6 KiB
LLVM
; RUN: llc < %s -mtriple=nvptx64 | FileCheck %s --check-prefixes CHECK,CHECK-APPROX-OPT,CHECK-SQRT-NOOPT
|
|
; RUN: llc < %s -mtriple=nvptx64 -nvptx-prec-sqrtf32=0 | FileCheck %s --check-prefixes CHECK,CHECK-APPROX-OPT,CHECK-SQRT-OPT
|
|
; RUN: llc < %s -mtriple=nvptx64 -nvptx-rsqrt-approx-opt=0 | FileCheck %s --check-prefixes CHECK,CHECK-APPROX-NOOPT,CHECK-SQRT-NOOPT
|
|
;
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 | %ptxas-verify %}
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -nvptx-prec-sqrtf32=0 | %ptxas-verify %}
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -nvptx-rsqrt-approx-opt=0 | %ptxas-verify %}
|
|
|
|
|
|
; CHECK-LABEL: .func{{.*}}test1
|
|
define float @test1(float %in) local_unnamed_addr {
|
|
; CHECK-APPROX-OPT: rsqrt.approx.f32
|
|
; CHECK-APPROX-NOOPT: sqrt.approx.f32
|
|
; CHECK-APPROX-NOOPT-NEXT: rcp.rn.f32
|
|
%sqrt = tail call float @llvm.nvvm.sqrt.approx.f(float %in)
|
|
%rsqrt = fdiv float 1.0, %sqrt
|
|
ret float %rsqrt
|
|
}
|
|
; CHECK-LABEL: .func{{.*}}test2
|
|
define float @test2(float %in) local_unnamed_addr {
|
|
; CHECK-APPROX-OPT: rsqrt.approx.ftz.f32
|
|
; CHECK-APPROX-NOOPT: sqrt.approx.ftz.f32
|
|
; CHECK-APPROX-NOOPT-NEXT: rcp.rn.f32
|
|
%sqrt = tail call float @llvm.nvvm.sqrt.approx.ftz.f(float %in)
|
|
%rsqrt = fdiv float 1.0, %sqrt
|
|
ret float %rsqrt
|
|
}
|
|
|
|
; CHECK-LABEL: .func{{.*}}test3
|
|
define float @test3(float %in) local_unnamed_addr {
|
|
; CHECK-SQRT-OPT: rsqrt.approx.f32
|
|
; CHECK-SQRT-NOOPT: sqrt.rn.f32
|
|
; CHECK-SQRT-NOOPT-NEXT: rcp.rn.f32
|
|
%sqrt = tail call float @llvm.nvvm.sqrt.f(float %in)
|
|
%rsqrt = fdiv float 1.0, %sqrt
|
|
ret float %rsqrt
|
|
}
|
|
|
|
; CHECK-LABEL: .func{{.*}}test4
|
|
define float @test4(float %in) local_unnamed_addr #0 {
|
|
; CHECK-SQRT-OPT: rsqrt.approx.ftz.f32
|
|
; CHECK-SQRT-NOOPT: sqrt.rn.ftz.f32
|
|
; CHECK-SQRT-NOOPT-NEXT: rcp.rn.ftz.f32
|
|
%sqrt = tail call float @llvm.nvvm.sqrt.f(float %in)
|
|
%rsqrt = fdiv float 1.0, %sqrt
|
|
ret float %rsqrt
|
|
}
|
|
|
|
; CHECK-LABEL: .func{{.*}}test5
|
|
define float @test5(float %in) local_unnamed_addr {
|
|
; CHECK-SQRT-OPT: rsqrt.approx.f32
|
|
; CHECK-SQRT-NOOPT: sqrt.rn.f32
|
|
; CHECK-SQRT-NOOPT-NEXT: rcp.rn.f32
|
|
%sqrt = tail call float @llvm.sqrt.f32(float %in)
|
|
%rsqrt = fdiv float 1.0, %sqrt
|
|
ret float %rsqrt
|
|
}
|
|
|
|
; CHECK-LABEL: .func{{.*}}test6
|
|
define float @test6(float %in) local_unnamed_addr #0 {
|
|
; CHECK-SQRT-OPT: rsqrt.approx.ftz.f32
|
|
; CHECK-SQRT-NOOPT: sqrt.rn.ftz.f32
|
|
; CHECK-SQRT-NOOPT-NEXT: rcp.rn.ftz.f32
|
|
%sqrt = tail call float @llvm.sqrt.f32(float %in)
|
|
%rsqrt = fdiv float 1.0, %sqrt
|
|
ret float %rsqrt
|
|
}
|
|
|
|
|
|
declare float @llvm.nvvm.sqrt.f(float)
|
|
declare float @llvm.nvvm.sqrt.approx.f(float)
|
|
declare float @llvm.nvvm.sqrt.approx.ftz.f(float)
|
|
declare float @llvm.sqrt.f32(float)
|
|
|
|
attributes #0 = { denormal_fpenv(float: preservesign) }
|