mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 03:02:36 +01:00
a859c18433
Summary: This allows us to reduce the number of different machine instruction opcodes, which reduces the table sizes and helps flatten the TableGen multiclass hierarchies. We can do this because for each hardware MIMG opcode, we have a full set of IMAGE_xxx_Vn_Vm machine instructions for all required sizes of vdata and vaddr registers. Instead of having separate D16 machine instructions, a packed D16 instructions loading e.g. 4 components can simply use the same V2 opcode variant that non-D16 instructions use. We still require a TSFlag for D16 buffer instructions, because the D16-ness of buffer instructions is part of the opcode. Renaming the flag should help avoid future confusion. The one non-obvious code change is that for gather4 instructions, the disassembler can no longer automatically decide whether to use a V2 or a V4 variant. The existing logic which choose the correct variant for other MIMG instruction is extended to cover gather4 as well. As a bonus, some of the assembler error messages are now more helpful (e.g., complaining about a wrong data size instead of a non-existing instruction). While we're at it, delete a whole bunch of dead legacy TableGen code. Change-Id: I89b02c2841c06f95e662541433e597f5d4553978 Reviewers: arsenm, rampitec, kzhuravl, artem.tamazov, dp, rtaylor Subscribers: wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D47434 llvm-svn: 335222
76 lines
2.1 KiB
YAML
76 lines
2.1 KiB
YAML
# RUN: llc -march=amdgcn -run-pass simple-register-coalescing -o - %s | FileCheck %s
|
|
# Check that %11 and %20 have been coalesced.
|
|
# CHECK: IMAGE_SAMPLE_C_D_O_V1_V16 %[[REG:[0-9]+]]
|
|
# CHECK: IMAGE_SAMPLE_C_D_O_V1_V16 %[[REG]]
|
|
|
|
---
|
|
name: main
|
|
alignment: 0
|
|
tracksRegLiveness: true
|
|
registers:
|
|
- { id: 0, class: sreg_64 }
|
|
- { id: 1, class: vgpr_32 }
|
|
- { id: 2, class: vgpr_32 }
|
|
- { id: 3, class: sreg_256 }
|
|
- { id: 4, class: sreg_128 }
|
|
- { id: 5, class: sreg_256 }
|
|
- { id: 6, class: sreg_128 }
|
|
- { id: 7, class: sreg_512 }
|
|
- { id: 9, class: vreg_512 }
|
|
- { id: 11, class: vreg_512 }
|
|
- { id: 18, class: vgpr_32 }
|
|
- { id: 20, class: vreg_512 }
|
|
- { id: 27, class: vgpr_32 }
|
|
liveins:
|
|
- { reg: '$sgpr2_sgpr3', virtual-reg: '%0' }
|
|
- { reg: '$vgpr2', virtual-reg: '%1' }
|
|
- { reg: '$vgpr3', virtual-reg: '%2' }
|
|
frameInfo:
|
|
isFrameAddressTaken: false
|
|
isReturnAddressTaken: false
|
|
hasStackMap: false
|
|
hasPatchPoint: false
|
|
stackSize: 0
|
|
offsetAdjustment: 0
|
|
maxAlignment: 0
|
|
adjustsStack: false
|
|
hasCalls: false
|
|
maxCallFrameSize: 0
|
|
hasOpaqueSPAdjustment: false
|
|
hasVAStart: false
|
|
hasMustTailInVarArgFunc: false
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr2_sgpr3, $vgpr2, $vgpr3
|
|
|
|
%0 = COPY $sgpr2_sgpr3
|
|
%1 = COPY $vgpr2
|
|
%2 = COPY $vgpr3
|
|
%3 = S_LOAD_DWORDX8_IMM %0, 0, 0
|
|
%4 = S_LOAD_DWORDX4_IMM %0, 12, 0
|
|
%5 = S_LOAD_DWORDX8_IMM %0, 16, 0
|
|
%6 = S_LOAD_DWORDX4_IMM %0, 28, 0
|
|
undef %7.sub0 = S_MOV_B32 212739
|
|
%20 = COPY %7
|
|
%11 = COPY %20
|
|
%11.sub1 = COPY %1
|
|
%11.sub2 = COPY %1
|
|
%11.sub3 = COPY %1
|
|
%11.sub4 = COPY %1
|
|
%11.sub5 = COPY %1
|
|
%11.sub6 = COPY %1
|
|
%11.sub7 = COPY %1
|
|
%11.sub8 = COPY %1
|
|
dead %18 = IMAGE_SAMPLE_C_D_O_V1_V16 %11, %3, %4, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec
|
|
%20.sub1 = COPY %2
|
|
%20.sub2 = COPY %2
|
|
%20.sub3 = COPY %2
|
|
%20.sub4 = COPY %2
|
|
%20.sub5 = COPY %2
|
|
%20.sub6 = COPY %2
|
|
%20.sub7 = COPY %2
|
|
%20.sub8 = COPY %2
|
|
dead %27 = IMAGE_SAMPLE_C_D_O_V1_V16 %20, %5, %6, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec
|
|
|
|
...
|