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
194 lines
7.7 KiB
YAML
194 lines
7.7 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
|
|
# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -verify-machineinstrs -run-pass=amdgpu-insert-delay-alu %s -o - | FileCheck %s
|
|
# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -verify-machineinstrs -passes=amdgpu-insert-delay-alu %s -o - | FileCheck %s
|
|
|
|
---
|
|
name: valu_dep_1
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: valu_dep_1
|
|
; CHECK: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_VALU_DEP_1
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: valu_dep_2
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: valu_dep_2
|
|
; CHECK: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: $vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_VALU_DEP_2
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: valu_dep_3
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: valu_dep_3
|
|
; CHECK: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: $vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
; CHECK-NEXT: $vgpr2 = V_ADD_U32_e32 $vgpr2, $vgpr2, implicit $exec
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_VALU_DEP_3
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
$vgpr2 = V_ADD_U32_e32 $vgpr2, $vgpr2, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: valu_dep_4
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: valu_dep_4
|
|
; CHECK: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: $vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
; CHECK-NEXT: $vgpr2 = V_ADD_U32_e32 $vgpr2, $vgpr2, implicit $exec
|
|
; CHECK-NEXT: $vgpr3 = V_ADD_U32_e32 $vgpr3, $vgpr3, implicit $exec
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_VALU_DEP_4
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
$vgpr2 = V_ADD_U32_e32 $vgpr2, $vgpr2, implicit $exec
|
|
$vgpr3 = V_ADD_U32_e32 $vgpr3, $vgpr3, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans32_dep_1
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: trans32_dep_1
|
|
; CHECK: $vgpr0 = V_EXP_F32_e32 $vgpr0, implicit $exec, implicit $mode
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_TRANS32_DEP_1
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_EXP_F32_e32 $vgpr0, implicit $exec, implicit $mode
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans32_dep_2
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: trans32_dep_2
|
|
; CHECK: $vgpr0 = V_EXP_F32_e32 $vgpr0, implicit $exec, implicit $mode
|
|
; CHECK-NEXT: $vgpr1 = V_EXP_F32_e32 $vgpr1, implicit $exec, implicit $mode
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_TRANS32_DEP_2
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_EXP_F32_e32 $vgpr0, implicit $exec, implicit $mode
|
|
$vgpr1 = V_EXP_F32_e32 $vgpr1, implicit $exec, implicit $mode
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans32_dep_3
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: trans32_dep_3
|
|
; CHECK: $vgpr0 = V_EXP_F32_e32 $vgpr0, implicit $exec, implicit $mode
|
|
; CHECK-NEXT: $vgpr1 = V_EXP_F32_e32 $vgpr1, implicit $exec, implicit $mode
|
|
; CHECK-NEXT: $vgpr2 = V_EXP_F32_e32 $vgpr2, implicit $exec, implicit $mode
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_TRANS32_DEP_3
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_EXP_F32_e32 $vgpr0, implicit $exec, implicit $mode
|
|
$vgpr1 = V_EXP_F32_e32 $vgpr1, implicit $exec, implicit $mode
|
|
$vgpr2 = V_EXP_F32_e32 $vgpr2, implicit $exec, implicit $mode
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: salu_cycle_1
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: salu_cycle_1
|
|
; CHECK: $sgpr0 = S_MOV_B32 0
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_SALU_CYCLE_1
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $sgpr0, $vgpr0, implicit $exec
|
|
$sgpr0 = S_MOV_B32 0
|
|
$vgpr0 = V_ADD_U32_e32 $sgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: valu_dep_1_same_trans32_dep_1
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: valu_dep_1_same_trans32_dep_1
|
|
; CHECK: $vgpr0 = V_EXP_F32_e32 $vgpr0, implicit $exec, implicit $mode
|
|
; CHECK-NEXT: $vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_TRANS32_DEP_1_skip_SAME_id1_VALU_DEP_1
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr1, implicit $exec
|
|
$vgpr0 = V_EXP_F32_e32 $vgpr0, implicit $exec, implicit $mode
|
|
$vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr1, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: valu_dep_1_same_salu_cycle_1
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: valu_dep_1_same_salu_cycle_1
|
|
; CHECK: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: $sgpr0 = S_MOV_B32 0
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_VALU_DEP_1_skip_SAME_id1_SALU_CYCLE_1
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $sgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$sgpr0 = S_MOV_B32 0
|
|
$vgpr0 = V_ADD_U32_e32 $sgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: valu_dep_1_next_valu_dep_1
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: valu_dep_1_next_valu_dep_1
|
|
; CHECK: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_VALU_DEP_1_skip_NEXT_id1_VALU_DEP_1
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: valu_dep_2_next_valu_dep_2
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: valu_dep_2_next_valu_dep_2
|
|
; CHECK: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: $vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_VALU_DEP_2_skip_NEXT_id1_VALU_DEP_2
|
|
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: $vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: valu_dep_2_skip_valu_dep_2
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: valu_dep_2_skip_valu_dep_2
|
|
; CHECK: $vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
; CHECK-NEXT: $vgpr2 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
; CHECK-NEXT: S_DELAY_ALU .id0_VALU_DEP_2_skip_SKIP_1_id1_VALU_DEP_2
|
|
; CHECK-NEXT: $vgpr1 = V_ADD_U32_e32 $vgpr0, $vgpr1, implicit $exec
|
|
; CHECK-NEXT: $vgpr4 = V_ADD_U32_e32 $vgpr3, $vgpr3, implicit $exec
|
|
; CHECK-NEXT: $vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
$vgpr0 = V_ADD_U32_e32 $vgpr0, $vgpr0, implicit $exec
|
|
$vgpr2 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
$vgpr1 = V_ADD_U32_e32 $vgpr0, $vgpr1, implicit $exec
|
|
$vgpr4 = V_ADD_U32_e32 $vgpr3, $vgpr3, implicit $exec
|
|
$vgpr1 = V_ADD_U32_e32 $vgpr1, $vgpr1, implicit $exec
|
|
...
|