forked from OSchip/llvm-project
169 lines
7.4 KiB
YAML
169 lines
7.4 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX8 %s
|
|
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX9 %s
|
|
|
|
---
|
|
name: umed3_s16_vvv
|
|
legalized: true
|
|
regBankSelected: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; GFX8-LABEL: name: umed3_s16_vvv
|
|
; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX8: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX8: [[V_MIN_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[V_MAX_U16_e64_]], [[V_MAX_U16_e64_1]], implicit $exec
|
|
; GFX8: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]]
|
|
; GFX9-LABEL: name: umed3_s16_vvv
|
|
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX9: [[V_MED3_U16_:%[0-9]+]]:vgpr_32 = V_MED3_U16 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $exec
|
|
; GFX9: S_ENDPGM 0, implicit [[V_MED3_U16_]]
|
|
%0:vgpr(s32) = COPY $vgpr0
|
|
%1:vgpr(s32) = COPY $vgpr1
|
|
%2:vgpr(s32) = COPY $vgpr2
|
|
%3:vgpr(s16) = G_TRUNC %0
|
|
%4:vgpr(s16) = G_TRUNC %1
|
|
%5:vgpr(s16) = G_TRUNC %2
|
|
|
|
%6:vgpr(s16) = G_UMAX %3, %4
|
|
%7:vgpr(s16) = G_UMIN %3, %4
|
|
%8:vgpr(s16) = G_UMAX %7, %5
|
|
%9:vgpr(s16) = G_UMIN %6, %8
|
|
|
|
S_ENDPGM 0, implicit %9
|
|
...
|
|
|
|
---
|
|
name: umed3_s16_vvv_multiuse0
|
|
legalized: true
|
|
regBankSelected: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; GFX8-LABEL: name: umed3_s16_vvv_multiuse0
|
|
; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX8: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX8: [[V_MIN_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[V_MAX_U16_e64_]], [[V_MAX_U16_e64_1]], implicit $exec
|
|
; GFX8: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]], implicit [[V_MAX_U16_e64_]]
|
|
; GFX9-LABEL: name: umed3_s16_vvv_multiuse0
|
|
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX9: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX9: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX9: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX9: [[V_MIN_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[V_MAX_U16_e64_]], [[V_MAX_U16_e64_1]], implicit $exec
|
|
; GFX9: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]], implicit [[V_MAX_U16_e64_]]
|
|
%0:vgpr(s32) = COPY $vgpr0
|
|
%1:vgpr(s32) = COPY $vgpr1
|
|
%2:vgpr(s32) = COPY $vgpr2
|
|
%3:vgpr(s16) = G_TRUNC %0
|
|
%4:vgpr(s16) = G_TRUNC %1
|
|
%5:vgpr(s16) = G_TRUNC %2
|
|
|
|
%6:vgpr(s16) = G_UMAX %3, %4
|
|
%7:vgpr(s16) = G_UMIN %3, %4
|
|
%8:vgpr(s16) = G_UMAX %7, %5
|
|
%9:vgpr(s16) = G_UMIN %6, %8
|
|
|
|
S_ENDPGM 0, implicit %9, implicit %6
|
|
...
|
|
|
|
---
|
|
name: umed3_s16_vvv_multiuse1
|
|
legalized: true
|
|
regBankSelected: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; GFX8-LABEL: name: umed3_s16_vvv_multiuse1
|
|
; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX8: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX8: [[V_MIN_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[V_MAX_U16_e64_]], [[V_MAX_U16_e64_1]], implicit $exec
|
|
; GFX8: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]], implicit [[V_MIN_U16_e64_]]
|
|
; GFX9-LABEL: name: umed3_s16_vvv_multiuse1
|
|
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX9: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX9: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX9: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX9: [[V_MIN_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[V_MAX_U16_e64_]], [[V_MAX_U16_e64_1]], implicit $exec
|
|
; GFX9: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]], implicit [[V_MIN_U16_e64_]]
|
|
%0:vgpr(s32) = COPY $vgpr0
|
|
%1:vgpr(s32) = COPY $vgpr1
|
|
%2:vgpr(s32) = COPY $vgpr2
|
|
%3:vgpr(s16) = G_TRUNC %0
|
|
%4:vgpr(s16) = G_TRUNC %1
|
|
%5:vgpr(s16) = G_TRUNC %2
|
|
|
|
%6:vgpr(s16) = G_UMAX %3, %4
|
|
%7:vgpr(s16) = G_UMIN %3, %4
|
|
%8:vgpr(s16) = G_UMAX %7, %5
|
|
%9:vgpr(s16) = G_UMIN %6, %8
|
|
|
|
S_ENDPGM 0, implicit %9, implicit %7
|
|
...
|
|
|
|
---
|
|
name: umed3_s16_vvv_multiuse2
|
|
legalized: true
|
|
regBankSelected: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; GFX8-LABEL: name: umed3_s16_vvv_multiuse2
|
|
; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX8: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX8: [[V_MIN_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[V_MAX_U16_e64_]], [[V_MAX_U16_e64_1]], implicit $exec
|
|
; GFX8: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]], implicit [[V_MAX_U16_e64_1]]
|
|
; GFX9-LABEL: name: umed3_s16_vvv_multiuse2
|
|
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX9: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX9: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX9: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX9: [[V_MIN_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[V_MAX_U16_e64_]], [[V_MAX_U16_e64_1]], implicit $exec
|
|
; GFX9: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]], implicit [[V_MAX_U16_e64_1]]
|
|
%0:vgpr(s32) = COPY $vgpr0
|
|
%1:vgpr(s32) = COPY $vgpr1
|
|
%2:vgpr(s32) = COPY $vgpr2
|
|
%3:vgpr(s16) = G_TRUNC %0
|
|
%4:vgpr(s16) = G_TRUNC %1
|
|
%5:vgpr(s16) = G_TRUNC %2
|
|
|
|
%6:vgpr(s16) = G_UMAX %3, %4
|
|
%7:vgpr(s16) = G_UMIN %3, %4
|
|
%8:vgpr(s16) = G_UMAX %7, %5
|
|
%9:vgpr(s16) = G_UMIN %6, %8
|
|
|
|
S_ENDPGM 0, implicit %9, implicit %8
|
|
...
|