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
65 lines
2.0 KiB
ArmAsm
65 lines
2.0 KiB
ArmAsm
// Verify that splitting a two-address DS load whose second destination crosses
|
|
// the active VGPR bank rebases that half to v0 under a temporary destination
|
|
// VGPR-MSB mode without losing the nonzero source or destination bank.
|
|
|
|
// 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: RESULT: SUCCESS
|
|
|
|
// RUN: %llvm-objdump -d %t.out.elf | %FileCheck --check-prefix=DISASM %s
|
|
// DISASM-LABEL: <test_ds_vgpr_msb>:
|
|
// DISASM: s_set_vgpr_msb 0x41
|
|
// DISASM-NEXT: s_branch
|
|
// DISASM: ds_load_b64 v[254:255], v88 offset:680
|
|
// DISASM-NEXT: s_set_vgpr_msb 0x4181
|
|
// DISASM-NEXT: ds_load_b64 v[0:1]{{.*v\[512:513\].*}}v88{{.*v344.*}}offset:688
|
|
// DISASM-NEXT: s_set_vgpr_msb 0x8141
|
|
// DISASM-NEXT: s_wait_dscnt 0x0
|
|
// DISASM: s_branch
|
|
|
|
// 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_ds_vgpr_msb
|
|
.p2align 8
|
|
.type test_ds_vgpr_msb,@function
|
|
test_ds_vgpr_msb:
|
|
s_set_vgpr_msb 0x41
|
|
ds_load_2addr_b64 v[254:257], v88 offset0:85 offset1:86
|
|
s_wait_dscnt 0x0
|
|
s_endpgm
|
|
.Ltest_ds_vgpr_msb_end:
|
|
.size test_ds_vgpr_msb, .Ltest_ds_vgpr_msb_end-test_ds_vgpr_msb
|
|
|
|
.rodata
|
|
.p2align 8
|
|
.amdhsa_kernel test_ds_vgpr_msb
|
|
.amdhsa_next_free_vgpr 688
|
|
.amdhsa_next_free_sgpr 2
|
|
.amdhsa_wavefront_size32 1
|
|
.end_amdhsa_kernel
|
|
|
|
.amdgpu_metadata
|
|
amdhsa.version:
|
|
- 3
|
|
- 0
|
|
amdhsa.kernels:
|
|
- .name: test_ds_vgpr_msb
|
|
.symbol: test_ds_vgpr_msb.kd
|
|
.sgpr_count: 2
|
|
.vgpr_count: 688
|
|
.kernarg_segment_size: 0
|
|
.group_segment_fixed_size: 0
|
|
.private_segment_fixed_size: 0
|
|
.kernarg_segment_align: 8
|
|
.wavefront_size: 32
|
|
.max_flat_workgroup_size: 256
|
|
.end_amdgpu_metadata
|