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
99 lines
5.3 KiB
YAML
99 lines
5.3 KiB
YAML
# RUN: llc -mtriple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 -start-before=amdgpu-lower-vgpr-encoding -o - %s | FileCheck -check-prefixes=GCN,ASM %s
|
|
# RUN: llc -mtriple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 -start-before=amdgpu-lower-vgpr-encoding -o - %s | llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 -filetype=obj -o - | llvm-objdump -d --mcpu=gfx1250 --mattr=+real-true16 - | FileCheck -check-prefixes=GCN,DIS %s
|
|
|
|
# ASM-LABEL: {{^}}high_vgprs:
|
|
# DIS-LABEL: <high_vgprs>:
|
|
---
|
|
name: high_vgprs
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
; ASM: %bb.0:
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v0.h, v1.h, v2.h
|
|
$vgpr0_hi16 = V_ADD_F16_t16_e64 0, undef $vgpr1_hi16, 0, undef $vgpr2_hi16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v0.l, v1.l, v2.l
|
|
$vgpr0_lo16 = V_ADD_F16_t16_e64 0, undef $vgpr1_lo16, 0, undef $vgpr2_lo16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v128.h, v129.h, v130.h
|
|
$vgpr128_hi16 = V_ADD_F16_t16_e64 0, undef $vgpr129_hi16, 0, undef $vgpr130_hi16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v128.l, v129.l, v130.l
|
|
$vgpr128_lo16 = V_ADD_F16_t16_e64 0, undef $vgpr129_lo16, 0, undef $vgpr130_lo16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: s_set_vgpr_msb 0x45
|
|
; ASM-SAME: ; msbs: dst=1 src0=1 src1=1 src2=0
|
|
; GCN-NEXT: v_add_f16_e64 v0.h /*v256.h*/, v1.h /*v257.h*/, v2.h /*v258.h*/
|
|
$vgpr256_hi16 = V_ADD_F16_t16_e64 0, undef $vgpr257_hi16, 0, undef $vgpr258_hi16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v0.l /*v256.l*/, v1.l /*v257.l*/, v2.l /*v258.l*/
|
|
$vgpr256_lo16 = V_ADD_F16_t16_e64 0, undef $vgpr257_lo16, 0, undef $vgpr258_lo16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v128.h /*v384.h*/, v129.h /*v385.h*/, v130.h /*v386.h*/
|
|
$vgpr384_hi16 = V_ADD_F16_t16_e64 0, undef $vgpr385_hi16, 0, undef $vgpr386_hi16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v128.l /*v384.l*/, v129.l /*v385.l*/, v130.l /*v386.l*/
|
|
$vgpr384_lo16 = V_ADD_F16_t16_e64 0, undef $vgpr385_lo16, 0, undef $vgpr386_lo16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: s_set_vgpr_msb 0x458a
|
|
; ASM-SAME: ; msbs: dst=2 src0=2 src1=2 src2=0
|
|
; GCN-NEXT: v_add_f16_e64 v0.h /*v512.h*/, v1.h /*v513.h*/, v2.h /*v514.h*/
|
|
$vgpr512_hi16 = V_ADD_F16_t16_e64 0, undef $vgpr513_hi16, 0, undef $vgpr514_hi16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v0.l /*v512.l*/, v1.l /*v513.l*/, v2.l /*v514.l*/
|
|
$vgpr512_lo16 = V_ADD_F16_t16_e64 0, undef $vgpr513_lo16, 0, undef $vgpr514_lo16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v128.h /*v640.h*/, v129.h /*v641.h*/, v130.h /*v642.h*/
|
|
$vgpr640_hi16 = V_ADD_F16_t16_e64 0, undef $vgpr641_hi16, 0, undef $vgpr642_hi16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v128.l /*v640.l*/, v129.l /*v641.l*/, v130.l /*v642.l*/
|
|
$vgpr640_lo16 = V_ADD_F16_t16_e64 0, undef $vgpr641_lo16, 0, undef $vgpr642_lo16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: s_set_vgpr_msb 0x8acf
|
|
; ASM-SAME: ; msbs: dst=3 src0=3 src1=3 src2=0
|
|
; GCN-NEXT: v_add_f16_e64 v0.h /*v768.h*/, v1.h /*v769.h*/, v2.h /*v770.h*/
|
|
$vgpr768_hi16 = V_ADD_F16_t16_e64 0, undef $vgpr769_hi16, 0, undef $vgpr770_hi16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v0.l /*v768.l*/, v1.l /*v769.l*/, v2.l /*v770.l*/
|
|
$vgpr768_lo16 = V_ADD_F16_t16_e64 0, undef $vgpr769_lo16, 0, undef $vgpr770_lo16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v128.h /*v896.h*/, v129.h /*v897.h*/, v130.h /*v898.h*/
|
|
$vgpr896_hi16 = V_ADD_F16_t16_e64 0, undef $vgpr897_hi16, 0, undef $vgpr898_hi16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_add_f16_e64 v128.l /*v896.l*/, v129.l /*v897.l*/, v130.l /*v898.l*/
|
|
$vgpr896_lo16 = V_ADD_F16_t16_e64 0, undef $vgpr897_lo16, 0, undef $vgpr898_lo16, 0, 0, 0, implicit $exec, implicit $mode
|
|
...
|
|
|
|
# ASM-LABEL: {{^}}fmaak_fmamk:
|
|
# DIS-LABEL: <fmaak_fmamk>:
|
|
---
|
|
name: fmaak_fmamk
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
; ASM: %bb.0:
|
|
|
|
; We use an extra instruction to set the MSB, and then we expect it to be reset to 0 (lower 16-bit).
|
|
|
|
; GCN: s_set_vgpr_msb 0xcf
|
|
; GCN-NEXT: v_add_f16_e64 v0.h /*v768.h*/, v1.h /*v769.h*/, v2.h /*v770.h*/
|
|
$vgpr768_hi16 = V_ADD_F16_t16_e64 0, undef $vgpr769_hi16, 0, undef $vgpr770_hi16, 0, 0, 0, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: s_set_vgpr_msb 0xcf00
|
|
; GCN-NEXT: v_fmamk_f16 v26.l, v56.l, 0x1, v58.l
|
|
$vgpr26_lo16 = V_FMAMK_F16_t16 undef $vgpr56_lo16, 1, undef $vgpr58_lo16, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_fmamk_f16 v0.l, v35.l, 0x1, v2.l
|
|
$vgpr0_lo16 = V_FMAMK_F16_t16 undef $vgpr35_lo16, 1, undef $vgpr2_lo16, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_fmamk_f16 v0.l, v2.l, 0x1, v6.l
|
|
$vgpr0_lo16 = V_FMAMK_F16_t16 undef $vgpr2_lo16, 1, undef $vgpr6_lo16, implicit $exec, implicit $mode
|
|
|
|
; GCN-NEXT: v_fmamk_f16 v5.l, v2.l, 0x1, v4.l
|
|
$vgpr5_lo16 = V_FMAMK_F16_t16 undef $vgpr2_lo16, 1, undef $vgpr4_lo16, implicit $exec, implicit $mode
|
|
|
|
; ASM: NumVgprs: 771
|
|
|
|
...
|