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
68 lines
3.8 KiB
YAML
68 lines
3.8 KiB
YAML
# RUN: llc -mtriple=amdgcn -mcpu=gfx1250 -start-before=amdgpu-insert-delay-alu %s -o - | FileCheck %s
|
|
|
|
---
|
|
name: wmma_xdl_twoaddr_trans
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: {{^}}wmma_xdl_twoaddr_trans:
|
|
; CHECK: %bb.0:
|
|
; CHECK-NEXT: v_wmma_f32_16x16x64_fp8_fp8 v[8:15], v[0:7], v[0:7], v[8:15]
|
|
; CHECK-NEXT: v_exp_f32_e32 v16, v16
|
|
; CHECK-NEXT: s_delay_alu instid0(TRANS32_DEP_2)
|
|
; CHECK-NEXT: v_add_nc_u32_e32 v17, v17, v8
|
|
liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7, $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16, $vgpr17
|
|
$vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = V_WMMA_F32_16X16X64_FP8_FP8_w32_twoaddr $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7, 8, $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, 0, 0, 0, 0, implicit $exec
|
|
$vgpr16 = V_EXP_F32_e32 $vgpr16, implicit $exec, implicit $mode
|
|
$vgpr17 = V_ADD_U32_e32 $vgpr17, $vgpr8, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: wmma_xdl_threeaddr_trans
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: {{^}}wmma_xdl_threeaddr_trans:
|
|
; CHECK: %bb.0:
|
|
; CHECK-NEXT: v_wmma_f32_16x16x64_fp8_fp8 v[8:15], v[0:7], v[0:7], v[16:23]
|
|
; CHECK-NEXT: v_exp_f32_e32 v24, v24
|
|
; CHECK-NEXT: s_delay_alu instid0(TRANS32_DEP_2)
|
|
; CHECK-NEXT: v_add_nc_u32_e32 v25, v25, v8
|
|
liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7, $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23, $vgpr24, $vgpr25
|
|
$vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = V_WMMA_F32_16X16X64_FP8_FP8_w32_threeaddr $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7, 8, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23, 0, 0, 0, 0, implicit $exec
|
|
$vgpr24 = V_EXP_F32_e32 $vgpr24, implicit $exec, implicit $mode
|
|
$vgpr25 = V_ADD_U32_e32 $vgpr25, $vgpr8, implicit $exec
|
|
...
|
|
|
|
name: swmmac_xdl_twoaddr_trans
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: {{^}}swmmac_xdl_twoaddr_trans:
|
|
; CHECK: %bb.0:
|
|
; CHECK-NEXT: v_swmmac_f16_16x16x128_bf8_bf8 v[24:27], v[0:7], v[8:23], v[28:29]
|
|
; CHECK-NEXT: v_exp_f32_e32 v30, v30
|
|
; CHECK-NEXT: s_delay_alu instid0(TRANS32_DEP_2)
|
|
; CHECK-NEXT: v_add_nc_u32_e32 v31, v31, v24
|
|
liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7, $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23, $vgpr24_vgpr25_vgpr26_vgpr27, $vgpr28, $vgpr29, $vgpr30, $vgpr31
|
|
$vgpr24_vgpr25_vgpr26_vgpr27 = V_SWMMAC_F16_16X16X128_BF8_BF8_w32_twoaddr $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7, $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23, $vgpr24_vgpr25_vgpr26_vgpr27, $vgpr28_vgpr29, 0, 0, 0, implicit $exec
|
|
$vgpr30 = V_EXP_F32_e32 $vgpr30, implicit $exec, implicit $mode
|
|
$vgpr31 = V_ADD_U32_e32 $vgpr31, $vgpr24, implicit $exec
|
|
...
|
|
|
|
name: wmma_non_xdl_large_data_valu
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: {{^}}wmma_non_xdl_large_data_valu:
|
|
; CHECK: %bb.0:
|
|
; CHECK-NEXT: v_wmma_f32_16x16x4_f32 v[4:11], v[0:1], v[2:3], v[4:11] matrix_b_reuse
|
|
; CHECK-NEXT: v_exp_f32_e32 v12, v12
|
|
; CHECK-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; CHECK-NEXT: v_add_nc_u32_e32 v13, v13, v8
|
|
liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7, $vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11, $vgpr12, $vgpr13
|
|
$vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11 = V_WMMA_F32_16X16X4_F32_w32_twoaddr $vgpr0_vgpr1, $vgpr2_vgpr3, 8, $vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11, 0, -1, 0, 0, implicit $exec
|
|
$vgpr12 = V_EXP_F32_e32 $vgpr12, implicit $exec, implicit $mode
|
|
$vgpr13 = V_ADD_U32_e32 $vgpr13, $vgpr8, implicit $exec
|
|
...
|