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
73 lines
1.9 KiB
ArmAsm
73 lines
1.9 KiB
ArmAsm
// COM: Test multi-DS stacking against a drain s_wait_dscnt: two
|
|
// COM: ds_load_2addr_stride64_b32 sites share a single s_wait_dscnt 0x0,
|
|
// COM: which is left in place across both splits (each split also emits its
|
|
// COM: own s_wait_dscnt 0x0 drain). Non-drain wait preservation is covered by
|
|
// COM: hotswap-trampoline-ds-pipelined.s.
|
|
|
|
// 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: Both DS2 instructions are replaced by s_branch to their respective
|
|
// COM: expansion sleds; the shared drain wait stays at 0x0.
|
|
// DISASM-LABEL: <test_multi_ds>:
|
|
// DISASM-NOT: ds_load_2addr_stride64_b32
|
|
// DISASM: s_branch
|
|
// DISASM: s_branch
|
|
// DISASM: s_wait_dscnt 0x0
|
|
|
|
// COM: Idempotency
|
|
// RUN: hotswap-rewrite %t.out.elf \
|
|
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
|
|
// RUN: --check-idempotent \
|
|
// RUN: | %FileCheck --check-prefix=IDEM %s
|
|
// IDEM: IDEMPOTENT: YES
|
|
|
|
.amdgcn_target "amdgcn-amd-amdhsa--gfx1250"
|
|
.text
|
|
.globl test_multi_ds
|
|
.p2align 8
|
|
.type test_multi_ds,@function
|
|
test_multi_ds:
|
|
ds_load_2addr_stride64_b32 v[0:1], v4 offset0:0 offset1:1
|
|
ds_load_2addr_stride64_b32 v[2:3], v4 offset0:2 offset1:3
|
|
s_wait_dscnt 0x0
|
|
s_endpgm
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
s_nop 0
|
|
.Ltest_multi_ds_end:
|
|
.size test_multi_ds, .Ltest_multi_ds_end-test_multi_ds
|
|
|
|
.rodata
|
|
.p2align 8
|
|
.amdhsa_kernel test_multi_ds
|
|
.amdhsa_next_free_vgpr 5
|
|
.amdhsa_next_free_sgpr 1
|
|
.end_amdhsa_kernel
|