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
59 lines
1.7 KiB
LLVM
59 lines
1.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc < %s -mtriple=nvptx64 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 | %ptxas-verify %}
|
|
|
|
target triple = "nvptx64-nvidia-cuda"
|
|
|
|
;; Check if fneg (fdiv 1, X) lowers to fneg (rcp.rn X).
|
|
|
|
define double @test1(double %in) {
|
|
; CHECK-LABEL: test1(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b64 %rd<4>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.b64 %rd1, [test1_param_0];
|
|
; CHECK-NEXT: rcp.rn.f64 %rd2, %rd1;
|
|
; CHECK-NEXT: neg.f64 %rd3, %rd2;
|
|
; CHECK-NEXT: st.param.b64 [func_retval0], %rd3;
|
|
; CHECK-NEXT: ret;
|
|
%div = fdiv double 1.000000e+00, %in
|
|
%neg = fsub double -0.000000e+00, %div
|
|
ret double %neg
|
|
}
|
|
|
|
;; Check if fdiv -1, X lowers to fneg (rcp.rn X).
|
|
|
|
define double @test2(double %in) {
|
|
; CHECK-LABEL: test2(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b64 %rd<4>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.b64 %rd1, [test2_param_0];
|
|
; CHECK-NEXT: rcp.rn.f64 %rd2, %rd1;
|
|
; CHECK-NEXT: neg.f64 %rd3, %rd2;
|
|
; CHECK-NEXT: st.param.b64 [func_retval0], %rd3;
|
|
; CHECK-NEXT: ret;
|
|
%div = fdiv double -1.000000e+00, %in
|
|
ret double %div
|
|
}
|
|
|
|
;; Check if fdiv 1, (fneg X) lowers to fneg (rcp.rn X).
|
|
|
|
define double @test3(double %in) {
|
|
; CHECK-LABEL: test3(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b64 %rd<4>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.b64 %rd1, [test3_param_0];
|
|
; CHECK-NEXT: rcp.rn.f64 %rd2, %rd1;
|
|
; CHECK-NEXT: neg.f64 %rd3, %rd2;
|
|
; CHECK-NEXT: st.param.b64 [func_retval0], %rd3;
|
|
; CHECK-NEXT: ret;
|
|
%neg = fsub double -0.000000e+00, %in
|
|
%div = fdiv double 1.000000e+00, %neg
|
|
ret double %div
|
|
}
|