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
ArmAsm
61 lines
1.9 KiB
ArmAsm
// COM: Test WMMA hazard with sufficient pre-existing v_nops: 8 v_nops
|
|
// COM: already present between WMMA (needs 8) and overlapping VALU.
|
|
// COM: No additional padding should be inserted.
|
|
|
|
// 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
|
|
|
|
// COM: 8 pre-existing v_nops between WMMA and the overlapping VALU already
|
|
// COM: meet A0's requirement, so the patch must not insert any padding.
|
|
// COM: The disassembly must remain WMMA -> 8 v_nops -> v_add_f32 ->
|
|
// COM: s_endpgm with no s_branch anywhere (no in-body branch, no trampoline
|
|
// COM: appended after s_endpgm). CHECK-COUNT-8 + CHECK-NEXT chain pins the
|
|
// COM: layout exactly; the trailing CHECK-NOT covers the post-kernel range.
|
|
// RUN: %llvm-objdump -d %t.out.elf | %FileCheck --check-prefix=DISASM %s
|
|
// DISASM: v_wmma_i32_16x16x64_iu8
|
|
// DISASM-COUNT-8: v_nop
|
|
// DISASM-NEXT: v_add_f32
|
|
// DISASM-NEXT: s_endpgm
|
|
// DISASM-NOT: s_branch
|
|
|
|
// COM: Idempotency
|
|
// 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_wmma_safe
|
|
.p2align 8
|
|
.type test_wmma_safe,@function
|
|
test_wmma_safe:
|
|
v_wmma_i32_16x16x64_iu8 v[16:23], v[0:7], v[8:15], v[16:23]
|
|
v_nop
|
|
v_nop
|
|
v_nop
|
|
v_nop
|
|
v_nop
|
|
v_nop
|
|
v_nop
|
|
v_nop
|
|
// 8 v_nops -- sufficient for A0, no patch needed
|
|
v_add_f32 v16, v0, v1
|
|
s_endpgm
|
|
.Ltest_wmma_safe_end:
|
|
.size test_wmma_safe, .Ltest_wmma_safe_end-test_wmma_safe
|
|
|
|
.rodata
|
|
.p2align 8
|
|
.amdhsa_kernel test_wmma_safe
|
|
.amdhsa_next_free_vgpr 24
|
|
.amdhsa_next_free_sgpr 2
|
|
.end_amdhsa_kernel
|