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
36 lines
1.3 KiB
ArmAsm
36 lines
1.3 KiB
ArmAsm
// A direct call can enter the WMMA either with the function-entry mode or the
|
|
// fallthrough can reach it after selecting a different destination bank. The
|
|
// K-split sources do not cross v255, but the second half replaces immediate
|
|
// src2 with dst and therefore still needs the ambiguous mode. Fail closed.
|
|
// This also exercises s_call_i64's unusual target operand layout in the shared
|
|
// direct-control-flow target index.
|
|
|
|
// 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: --expect-status ERROR 2>&1 \
|
|
// RUN: | %FileCheck --check-prefix=CHECK %s
|
|
// CHECK-LABEL: WMMA split: cannot determine VGPR-MSB mode
|
|
// CHECK: RESULT: ERROR
|
|
|
|
.amdgcn_target "amdgcn-amd-amdhsa--gfx1250"
|
|
.text
|
|
.globl test_wmma_vgpr_msb_merge
|
|
.p2align 8
|
|
.type test_wmma_vgpr_msb_merge,@function
|
|
test_wmma_vgpr_msb_merge:
|
|
s_call_i64 s[0:1], .Lwmma
|
|
s_set_vgpr_msb 0x40
|
|
.Lwmma:
|
|
v_wmma_f32_16x16x128_fp8_fp8 v[32:39], v[0:15], v[16:31], 0
|
|
s_endpgm
|
|
.Ltest_wmma_vgpr_msb_merge_end:
|
|
.size test_wmma_vgpr_msb_merge, .Ltest_wmma_vgpr_msb_merge_end-test_wmma_vgpr_msb_merge
|
|
|
|
.rodata
|
|
.p2align 8
|
|
.amdhsa_kernel test_wmma_vgpr_msb_merge
|
|
.amdhsa_next_free_vgpr 266
|
|
.amdhsa_next_free_sgpr 2
|
|
.end_amdhsa_kernel
|