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
61 lines
1.9 KiB
LLVM
61 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}
|
|
|
|
define float @foo(<2 x float> %a) {
|
|
; CHECK-LABEL: foo(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<6>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.v2.b32 {%r1, %r2}, [foo_param_0];
|
|
; CHECK-NEXT: mul.rn.f32 %r3, %r2, %r2;
|
|
; CHECK-NEXT: mul.rn.f32 %r4, %r1, %r1;
|
|
; CHECK-NEXT: add.rn.f32 %r5, %r4, %r3;
|
|
; CHECK-NEXT: st.param.b32 [func_retval0], %r5;
|
|
; CHECK-NEXT: ret;
|
|
%t1 = fmul <2 x float> %a, %a
|
|
%t2 = extractelement <2 x float> %t1, i32 0
|
|
%t3 = extractelement <2 x float> %t1, i32 1
|
|
%t4 = fadd float %t2, %t3
|
|
ret float %t4
|
|
}
|
|
|
|
|
|
define float @bar(<4 x float> %a) {
|
|
; CHECK-LABEL: bar(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<8>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.v4.b32 {%r1, %r2, %r3, %r4}, [bar_param_0];
|
|
; CHECK-NEXT: mul.rn.f32 %r5, %r2, %r2;
|
|
; CHECK-NEXT: mul.rn.f32 %r6, %r1, %r1;
|
|
; CHECK-NEXT: add.rn.f32 %r7, %r6, %r5;
|
|
; CHECK-NEXT: st.param.b32 [func_retval0], %r7;
|
|
; CHECK-NEXT: ret;
|
|
%t1 = fmul <4 x float> %a, %a
|
|
%t2 = extractelement <4 x float> %t1, i32 0
|
|
%t3 = extractelement <4 x float> %t1, i32 1
|
|
%t4 = fadd float %t2, %t3
|
|
ret float %t4
|
|
}
|
|
|
|
|
|
define <4 x float> @baz(<4 x float> %a) {
|
|
; CHECK-LABEL: baz(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<9>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.v4.b32 {%r1, %r2, %r3, %r4}, [baz_param_0];
|
|
; CHECK-NEXT: mul.rn.f32 %r5, %r4, %r4;
|
|
; CHECK-NEXT: mul.rn.f32 %r6, %r3, %r3;
|
|
; CHECK-NEXT: mul.rn.f32 %r7, %r2, %r2;
|
|
; CHECK-NEXT: mul.rn.f32 %r8, %r1, %r1;
|
|
; CHECK-NEXT: st.param.v4.b32 [func_retval0], {%r8, %r7, %r6, %r5};
|
|
; CHECK-NEXT: ret;
|
|
%t1 = fmul <4 x float> %a, %a
|
|
ret <4 x float> %t1
|
|
}
|