b982ba2a6e
Due to the encoding changes in GFX11, we had a hack in place that
disables the use of VGPRs above 128. This patch removes the need for
that hack.
We introduce a new register class VGPR_32_Lo128 which is used for 16-bit
operands of VOP1, VOP2, and VOPC instructions. This register class only has the
low 128 VGPRs, but is otherwise identical to VGPR_32. Therefore, 16-bit VOP1,
VOP2, and VOPC instructions are correctly limited to use the first 128
VGPRs, while the other instructions can freely use all 256.
We introduce new pseduo-instructions used on GFX11 which have the suffix
t16 (True 16) to use the VGPR_32_Lo128 register class.
Reviewed By: foad, rampitec, #amdgpu
Differential Revision: https://reviews.llvm.org/D133723
218 lines
10 KiB
YAML
218 lines
10 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
|
|
# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX9 %s
|
|
# RUN: llc -march=amdgcn -mcpu=gfx1100 -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX11 %s
|
|
|
|
---
|
|
name: umed3_s16_vvv
|
|
legalized: true
|
|
regBankSelected: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; GFX8-LABEL: name: umed3_s16_vvv
|
|
; GFX8: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX8-NEXT: {{ $}}
|
|
; GFX8-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX8-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX8-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX8-NEXT: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8-NEXT: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8-NEXT: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX8-NEXT: [[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-NEXT: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]]
|
|
; GFX9-LABEL: name: umed3_s16_vvv
|
|
; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX9-NEXT: {{ $}}
|
|
; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX9-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX9-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX9-NEXT: [[V_MED3_U16_e64_:%[0-9]+]]:vgpr_32 = V_MED3_U16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $exec
|
|
; GFX9-NEXT: S_ENDPGM 0, implicit [[V_MED3_U16_e64_]]
|
|
; GFX11-LABEL: name: umed3_s16_vvv
|
|
; GFX11: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX11-NEXT: {{ $}}
|
|
; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX11-NEXT: [[V_MED3_U16_e64_:%[0-9]+]]:vgpr_32 = V_MED3_U16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $exec
|
|
; GFX11-NEXT: S_ENDPGM 0, implicit [[V_MED3_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
|
|
...
|
|
|
|
---
|
|
name: umed3_s16_vvv_multiuse0
|
|
legalized: true
|
|
regBankSelected: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; GFX8-LABEL: name: umed3_s16_vvv_multiuse0
|
|
; GFX8: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX8-NEXT: {{ $}}
|
|
; GFX8-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX8-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX8-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX8-NEXT: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8-NEXT: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8-NEXT: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX8-NEXT: [[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-NEXT: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]], implicit [[V_MAX_U16_e64_]]
|
|
; GFX9-LABEL: name: umed3_s16_vvv_multiuse0
|
|
; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX9-NEXT: {{ $}}
|
|
; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX9-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX9-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX9-NEXT: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX9-NEXT: [[V_MED3_U16_e64_:%[0-9]+]]:vgpr_32 = V_MED3_U16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $exec
|
|
; GFX9-NEXT: S_ENDPGM 0, implicit [[V_MED3_U16_e64_]], implicit [[V_MAX_U16_e64_]]
|
|
; GFX11-LABEL: name: umed3_s16_vvv_multiuse0
|
|
; GFX11: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX11-NEXT: {{ $}}
|
|
; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX11-NEXT: [[V_MAX_U16_t16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_t16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX11-NEXT: [[V_MED3_U16_e64_:%[0-9]+]]:vgpr_32 = V_MED3_U16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $exec
|
|
; GFX11-NEXT: S_ENDPGM 0, implicit [[V_MED3_U16_e64_]], implicit [[V_MAX_U16_t16_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: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX8-NEXT: {{ $}}
|
|
; GFX8-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX8-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX8-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX8-NEXT: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8-NEXT: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8-NEXT: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX8-NEXT: [[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-NEXT: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]], implicit [[V_MIN_U16_e64_]]
|
|
; GFX9-LABEL: name: umed3_s16_vvv_multiuse1
|
|
; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX9-NEXT: {{ $}}
|
|
; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX9-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX9-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX9-NEXT: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX9-NEXT: [[V_MED3_U16_e64_:%[0-9]+]]:vgpr_32 = V_MED3_U16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $exec
|
|
; GFX9-NEXT: S_ENDPGM 0, implicit [[V_MED3_U16_e64_]], implicit [[V_MIN_U16_e64_]]
|
|
; GFX11-LABEL: name: umed3_s16_vvv_multiuse1
|
|
; GFX11: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX11-NEXT: {{ $}}
|
|
; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX11-NEXT: [[V_MIN_U16_t16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_t16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX11-NEXT: [[V_MED3_U16_e64_:%[0-9]+]]:vgpr_32 = V_MED3_U16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $exec
|
|
; GFX11-NEXT: S_ENDPGM 0, implicit [[V_MED3_U16_e64_]], implicit [[V_MIN_U16_t16_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: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX8-NEXT: {{ $}}
|
|
; GFX8-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX8-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX8-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX8-NEXT: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8-NEXT: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX8-NEXT: [[V_MAX_U16_e64_1:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX8-NEXT: [[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-NEXT: S_ENDPGM 0, implicit [[V_MIN_U16_e64_1]], implicit [[V_MAX_U16_e64_1]]
|
|
; GFX9-LABEL: name: umed3_s16_vvv_multiuse2
|
|
; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX9-NEXT: {{ $}}
|
|
; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX9-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX9-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX9-NEXT: [[V_MIN_U16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX9-NEXT: [[V_MAX_U16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_e64 [[V_MIN_U16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX9-NEXT: [[V_MED3_U16_e64_:%[0-9]+]]:vgpr_32 = V_MED3_U16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $exec
|
|
; GFX9-NEXT: S_ENDPGM 0, implicit [[V_MED3_U16_e64_]], implicit [[V_MAX_U16_e64_]]
|
|
; GFX11-LABEL: name: umed3_s16_vvv_multiuse2
|
|
; GFX11: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; GFX11-NEXT: {{ $}}
|
|
; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; GFX11-NEXT: [[V_MIN_U16_t16_e64_:%[0-9]+]]:vgpr_32 = V_MIN_U16_t16_e64 [[COPY]], [[COPY1]], implicit $exec
|
|
; GFX11-NEXT: [[V_MAX_U16_t16_e64_:%[0-9]+]]:vgpr_32 = V_MAX_U16_t16_e64 [[V_MIN_U16_t16_e64_]], [[COPY2]], implicit $exec
|
|
; GFX11-NEXT: [[V_MED3_U16_e64_:%[0-9]+]]:vgpr_32 = V_MED3_U16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $exec
|
|
; GFX11-NEXT: S_ENDPGM 0, implicit [[V_MED3_U16_e64_]], implicit [[V_MAX_U16_t16_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 %8
|
|
...
|