Files
TheRock/compiler/amd-llvm/amd/comgr/test-lit/hotswap/rewriter/hotswap-inplace-async.s
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

53 lines
1.7 KiB
ArmAsm

// COM: Test HotSwap in-place patch: cluster_load_async_to_lds_{b8,b32,b64,b128}
// COM: -> global_load_async_to_lds_{b8,b32,b64,b128}.
// RUN: %clang -target amdgcn-amd-amdhsa -mcpu=gfx1250 -nostdlib %s -o %t.elf
// RUN: hotswap-rewrite %t.elf \
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
// RUN: --output %t.out.elf \
// RUN: | %FileCheck --check-prefix=API %s
// API: RESULT: SUCCESS
// RUN: %llvm-objdump -d %t.out.elf | %FileCheck --check-prefix=DISASM %s
// COM: All cluster_load_async_to_lds variants should be replaced
// DISASM-NOT: cluster_load_async_to_lds
// DISASM-DAG: global_load_async_to_lds_b8
// DISASM-DAG: global_load_async_to_lds_b32
// DISASM-DAG: global_load_async_to_lds_b64
// DISASM-DAG: global_load_async_to_lds_b128
// COM: Idempotency: output should be identical on second rewrite.
// RUN: hotswap-rewrite %t.out.elf \
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
// RUN: --output %t.out2.elf \
// RUN: | %FileCheck --check-prefix=API2 %s
// API2: RESULT: SUCCESS
// RUN: cmp %t.out.elf %t.out2.elf
.amdgcn_target "amdgcn-amd-amdhsa--gfx1250"
.text
.globl test_async_kernel
.p2align 8
.type test_async_kernel,@function
test_async_kernel:
cluster_load_async_to_lds_b8 v1, v[2:3], off
s_wait_loadcnt 0x0
cluster_load_async_to_lds_b32 v1, v[2:3], off
s_wait_loadcnt 0x0
cluster_load_async_to_lds_b64 v1, v[2:3], off
s_wait_loadcnt 0x0
cluster_load_async_to_lds_b128 v1, v[2:3], off
s_wait_loadcnt 0x0
s_endpgm
.Ltest_async_kernel_end:
.size test_async_kernel, .Ltest_async_kernel_end-test_async_kernel
.rodata
.p2align 8
.amdhsa_kernel test_async_kernel
.amdhsa_next_free_vgpr 4
.amdhsa_next_free_sgpr 2
.end_amdhsa_kernel