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
48 lines
2.1 KiB
ArmAsm
48 lines
2.1 KiB
ArmAsm
// A mandatory K=128 WMMA split in a block proven unreachable by a
|
|
// materialized-PC jump (s_get_pc_i64 / s_add_nc_u64 / s_set_pc_i64) out of the
|
|
// function must succeed using the ABI entry VGPR-MSB mode, not fail closed:
|
|
// the code never executes, so its incoming mode is semantically unobservable,
|
|
// but the A0-incompatible opcode must still be legalized. The first WMMA
|
|
// follows an explicit dead MODE write; the second has no local MODE write.
|
|
|
|
// RUN: %clang -target amdgcn-amd-amdhsa -mcpu=gfx1250 -nostdlib %s -o %t.elf
|
|
// RUN: env AMD_COMGR_EMIT_VERBOSE_LOGS=1 hotswap-rewrite %t.elf \
|
|
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
|
|
// RUN: --output %t.out.elf 2>&1 | %FileCheck --check-prefix=API %s
|
|
// API-NOT: error:
|
|
// API-COUNT-2: WMMA split: patched v_wmma_f32_16x16x128_fp8_fp8
|
|
// API: applied 2 instruction patches
|
|
// API: RESULT: SUCCESS
|
|
|
|
// RUN: %llvm-objdump -d %t.out.elf | %FileCheck --check-prefix=DISASM %s
|
|
// The A0-incompatible K=128 form must not survive; both halves are K=64. These
|
|
// operands stay in bank 0, so no s_set_vgpr_msb bracketing is required.
|
|
// DISASM-NOT: v_wmma_f32_16x16x128_fp8_fp8
|
|
// DISASM: v_wmma_f32_16x16x64_fp8_fp8
|
|
|
|
// RUN: hotswap-rewrite %t.out.elf \
|
|
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
|
|
// RUN: --check-idempotent | %FileCheck --check-prefix=IDEM %s
|
|
// IDEM: IDEMPOTENT: YES
|
|
|
|
.amdgcn_target "amdgcn-amd-amdhsa--gfx1250"
|
|
.text
|
|
.globl test_wmma_unreachable_cfg
|
|
.p2align 8
|
|
.type test_wmma_unreachable_cfg,@function
|
|
test_wmma_unreachable_cfg:
|
|
// Generated get-PC/add/set-PC with a statically known target outside the
|
|
// function, so the instructions below are CFG-unreachable.
|
|
s_get_pc_i64 s[0:1]
|
|
s_add_nc_u64 s[0:1], s[0:1], 0x1000
|
|
s_set_pc_i64 s[0:1]
|
|
|
|
s_set_vgpr_msb 0
|
|
s_delay_alu instid0(VALU_DEP_1)
|
|
v_wmma_f32_16x16x128_fp8_fp8 v[32:39], v[0:15], v[16:31], 0
|
|
s_delay_alu instid0(VALU_DEP_1)
|
|
v_wmma_f32_16x16x128_fp8_fp8 v[32:39], v[0:15], v[16:31], 0
|
|
s_endpgm
|
|
.Ltest_wmma_unreachable_cfg_end:
|
|
.size test_wmma_unreachable_cfg, .Ltest_wmma_unreachable_cfg_end-test_wmma_unreachable_cfg
|