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
81 lines
2.4 KiB
LLVM
81 lines
2.4 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 void @foo1(<2 x float> %val, ptr %ptr) {
|
|
; CHECK-LABEL: foo1(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<3>;
|
|
; CHECK-NEXT: .reg .b64 %rd<2>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.v2.b32 {%r1, %r2}, [foo1_param_0];
|
|
; CHECK-NEXT: ld.param.b64 %rd1, [foo1_param_1];
|
|
; CHECK-NEXT: st.v2.b32 [%rd1], {%r1, %r2};
|
|
; CHECK-NEXT: ret;
|
|
store <2 x float> %val, ptr %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @foo2(<4 x float> %val, ptr %ptr) {
|
|
; CHECK-LABEL: foo2(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<5>;
|
|
; CHECK-NEXT: .reg .b64 %rd<2>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.v4.b32 {%r1, %r2, %r3, %r4}, [foo2_param_0];
|
|
; CHECK-NEXT: ld.param.b64 %rd1, [foo2_param_1];
|
|
; CHECK-NEXT: st.v4.b32 [%rd1], {%r1, %r2, %r3, %r4};
|
|
; CHECK-NEXT: ret;
|
|
store <4 x float> %val, ptr %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @foo3(<2 x i32> %val, ptr %ptr) {
|
|
; CHECK-LABEL: foo3(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<3>;
|
|
; CHECK-NEXT: .reg .b64 %rd<2>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.v2.b32 {%r1, %r2}, [foo3_param_0];
|
|
; CHECK-NEXT: ld.param.b64 %rd1, [foo3_param_1];
|
|
; CHECK-NEXT: st.v2.b32 [%rd1], {%r1, %r2};
|
|
; CHECK-NEXT: ret;
|
|
store <2 x i32> %val, ptr %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @foo4(<4 x i32> %val, ptr %ptr) {
|
|
; CHECK-LABEL: foo4(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<5>;
|
|
; CHECK-NEXT: .reg .b64 %rd<2>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.v4.b32 {%r1, %r2, %r3, %r4}, [foo4_param_0];
|
|
; CHECK-NEXT: ld.param.b64 %rd1, [foo4_param_1];
|
|
; CHECK-NEXT: st.v4.b32 [%rd1], {%r1, %r2, %r3, %r4};
|
|
; CHECK-NEXT: ret;
|
|
store <4 x i32> %val, ptr %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @v16i8(ptr %a, ptr %b) {
|
|
; CHECK-LABEL: v16i8(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b32 %r<5>;
|
|
; CHECK-NEXT: .reg .b64 %rd<3>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.b64 %rd1, [v16i8_param_0];
|
|
; CHECK-NEXT: ld.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
|
|
; CHECK-NEXT: ld.param.b64 %rd2, [v16i8_param_1];
|
|
; CHECK-NEXT: st.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
|
|
; CHECK-NEXT: ret;
|
|
%v = load <16 x i8>, ptr %a
|
|
store <16 x i8> %v, ptr %b
|
|
ret void
|
|
}
|