mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
6705a324ed
The hardware has created a real mess in the naming for add/sub, which have been renamed basically every generation. Switch the carry out pseudos to have the gfx9/gfx10 names. We were using the original SI/CI v_add_i32/v_sub_i32 names. Later targets reintroduced these names as carryless instructions with a saturating clamp bit, which we do not define. Do this rename so we can unambiguously add these missing instructions. The carry-in versions should also be renamed, but at least those had a consistent _u32 name to begin with. The 16-bit instructions were also renamed, but aren't ambiguous. This does regress assembler error message quality in some cases. In mismatched wave32/wave64 situations, this will switch from "unsupported instruction" to "invalid operand", with the error pointing at the wrong position. I couldn't quite follow how the assembler selects these, but the previous behavior seemed accidental to me. It looked like there was a partial attempt to handle this which was never completed (i.e. there is an AMDGPUOperand::isBoolReg but it isn't used for anything).
71 lines
3.3 KiB
YAML
71 lines
3.3 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -march=amdgcn -mcpu=tahiti -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX6 %s
|
|
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX6 %s
|
|
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX9 %s
|
|
# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX10 %s
|
|
|
|
---
|
|
name: sub_s32
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0, $sgpr1, $vgpr0, $vgpr3_vgpr4
|
|
|
|
|
|
; GFX6-LABEL: name: sub_s32
|
|
; GFX6: liveins: $sgpr0, $sgpr1, $vgpr0, $vgpr3_vgpr4
|
|
; GFX6: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
|
|
; GFX6: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
|
|
; GFX6: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX6: [[S_SUB_I32_:%[0-9]+]]:sreg_32 = S_SUB_I32 [[COPY]], [[COPY1]], implicit-def $scc
|
|
; GFX6: %7:vgpr_32, dead %12:sreg_64_xexec = V_SUB_CO_U32_e64 [[COPY2]], [[S_SUB_I32_]], 0, implicit $exec
|
|
; GFX6: %8:vgpr_32, dead %11:sreg_64_xexec = V_SUB_CO_U32_e64 [[S_SUB_I32_]], %7, 0, implicit $exec
|
|
; GFX6: %9:vgpr_32, dead %10:sreg_64_xexec = V_SUB_CO_U32_e64 %8, [[COPY2]], 0, implicit $exec
|
|
; GFX6: S_ENDPGM 0, implicit %9
|
|
; GFX9-LABEL: name: sub_s32
|
|
; GFX9: liveins: $sgpr0, $sgpr1, $vgpr0, $vgpr3_vgpr4
|
|
; GFX9: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
|
|
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX9: [[S_SUB_I32_:%[0-9]+]]:sreg_32 = S_SUB_I32 [[COPY]], [[COPY1]], implicit-def $scc
|
|
; GFX9: [[V_SUB_U32_e64_:%[0-9]+]]:vgpr_32 = V_SUB_U32_e64 [[COPY2]], [[S_SUB_I32_]], 0, implicit $exec
|
|
; GFX9: [[V_SUB_U32_e64_1:%[0-9]+]]:vgpr_32 = V_SUB_U32_e64 [[S_SUB_I32_]], [[V_SUB_U32_e64_]], 0, implicit $exec
|
|
; GFX9: [[V_SUB_U32_e64_2:%[0-9]+]]:vgpr_32 = V_SUB_U32_e64 [[V_SUB_U32_e64_1]], [[COPY2]], 0, implicit $exec
|
|
; GFX9: S_ENDPGM 0, implicit [[V_SUB_U32_e64_2]]
|
|
; GFX10-LABEL: name: sub_s32
|
|
; GFX10: liveins: $sgpr0, $sgpr1, $vgpr0, $vgpr3_vgpr4
|
|
; GFX10: $vcc_hi = IMPLICIT_DEF
|
|
; GFX10: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
|
|
; GFX10: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
|
|
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; GFX10: [[S_SUB_I32_:%[0-9]+]]:sreg_32 = S_SUB_I32 [[COPY]], [[COPY1]], implicit-def $scc
|
|
; GFX10: [[V_SUB_U32_e64_:%[0-9]+]]:vgpr_32 = V_SUB_U32_e64 [[COPY2]], [[S_SUB_I32_]], 0, implicit $exec
|
|
; GFX10: [[V_SUB_U32_e64_1:%[0-9]+]]:vgpr_32 = V_SUB_U32_e64 [[S_SUB_I32_]], [[V_SUB_U32_e64_]], 0, implicit $exec
|
|
; GFX10: [[V_SUB_U32_e64_2:%[0-9]+]]:vgpr_32 = V_SUB_U32_e64 [[V_SUB_U32_e64_1]], [[COPY2]], 0, implicit $exec
|
|
; GFX10: S_ENDPGM 0, implicit [[V_SUB_U32_e64_2]]
|
|
%0:sgpr(s32) = COPY $sgpr0
|
|
%1:sgpr(s32) = COPY $sgpr1
|
|
%2:vgpr(s32) = COPY $vgpr0
|
|
%3:vgpr(p1) = COPY $vgpr3_vgpr4
|
|
%4:sgpr(s32) = G_CONSTANT i32 1
|
|
%5:sgpr(s32) = G_CONSTANT i32 4096
|
|
|
|
; sub ss
|
|
%6:sgpr(s32) = G_SUB %0, %1
|
|
|
|
; sub vs
|
|
%7:vgpr(s32) = G_SUB %2, %6
|
|
|
|
; sub sv
|
|
%8:vgpr(s32) = G_SUB %6, %7
|
|
|
|
; sub vv
|
|
%9:vgpr(s32) = G_SUB %8, %2
|
|
|
|
S_ENDPGM 0, implicit %9
|
|
|
|
...
|