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
47 lines
2.2 KiB
LLVM
47 lines
2.2 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_100 -mattr=+ptx86 | FileCheck --check-prefixes=CHECK,CHECK-PTX64 %s
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_100 -mattr=+ptx86 --nvptx-short-ptr | FileCheck --check-prefixes=CHECK,CHECK-PTX-SHARED32 %s
|
|
; RUN: %if ptxas-sm_100 && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100 -mattr=+ptx86 | %ptxas-verify -arch=sm_100 %}
|
|
; RUN: %if ptxas-sm_100 && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100 -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_100 %}
|
|
|
|
declare void @llvm.nvvm.st.bulk(ptr, i64, i64)
|
|
define void @st_bulk(ptr %dest_addr, i64 %size) {
|
|
; CHECK-LABEL: st_bulk(
|
|
; CHECK: {
|
|
; CHECK-NEXT: .reg .b64 %rd<3>;
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: // %bb.0:
|
|
; CHECK-NEXT: ld.param.b64 %rd1, [st_bulk_param_0];
|
|
; CHECK-NEXT: ld.param.b64 %rd2, [st_bulk_param_1];
|
|
; CHECK-NEXT: st.bulk [%rd1], %rd2, 0;
|
|
; CHECK-NEXT: ret;
|
|
call void @llvm.nvvm.st.bulk(ptr %dest_addr, i64 %size, i64 0)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.nvvm.st.bulk.shared.cta(ptr addrspace(3), i64, i64)
|
|
define void @st_bulk_shared_cta(ptr addrspace(3) %dest_addr, i64 %size) {
|
|
; CHECK-PTX64-LABEL: st_bulk_shared_cta(
|
|
; CHECK-PTX64: {
|
|
; CHECK-PTX64-NEXT: .reg .b64 %rd<3>;
|
|
; CHECK-PTX64-EMPTY:
|
|
; CHECK-PTX64-NEXT: // %bb.0:
|
|
; CHECK-PTX64-NEXT: ld.param.b64 %rd1, [st_bulk_shared_cta_param_0];
|
|
; CHECK-PTX64-NEXT: ld.param.b64 %rd2, [st_bulk_shared_cta_param_1];
|
|
; CHECK-PTX64-NEXT: st.bulk.shared::cta [%rd1], %rd2, 0;
|
|
; CHECK-PTX64-NEXT: ret;
|
|
;
|
|
; CHECK-PTX-SHARED32-LABEL: st_bulk_shared_cta(
|
|
; CHECK-PTX-SHARED32: {
|
|
; CHECK-PTX-SHARED32-NEXT: .reg .b32 %r<2>;
|
|
; CHECK-PTX-SHARED32-NEXT: .reg .b64 %rd<2>;
|
|
; CHECK-PTX-SHARED32-EMPTY:
|
|
; CHECK-PTX-SHARED32-NEXT: // %bb.0:
|
|
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r1, [st_bulk_shared_cta_param_0];
|
|
; CHECK-PTX-SHARED32-NEXT: ld.param.b64 %rd1, [st_bulk_shared_cta_param_1];
|
|
; CHECK-PTX-SHARED32-NEXT: st.bulk.shared::cta [%r1], %rd1, 0;
|
|
; CHECK-PTX-SHARED32-NEXT: ret;
|
|
call void @llvm.nvvm.st.bulk.shared.cta(ptr addrspace(3) %dest_addr, i64 %size, i64 0)
|
|
ret void
|
|
}
|