[AMDGPU] SDWA: remove support for VOP2 instructions that have only 64-bit encoding
Summary:
Despite that this instructions are listed in VOP2, they are treated as VOP3 in specs. They should not support SDWA.
There are no real instructions for them, but there are pseudo instructions.
Reviewers: arsenm, vpykhtin, cfang
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34403
llvm-svn: 305999
2017-06-22 20:42:14 +08:00
|
|
|
# RUN: llc -march=amdgcn -mcpu=kaveri -run-pass=si-peephole-sdwa -o - %s | FileCheck -check-prefix=CI -check-prefix=GCN %s
|
|
|
|
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=si-peephole-sdwa -o - %s | FileCheck -check-prefix=VI -check-prefix=GCN %s
|
|
|
|
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=si-peephole-sdwa -o - %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
|
|
|
|
|
|
|
|
# No conversion for VOP2 instructions that have only 64-bit encoding
|
|
|
|
|
|
|
|
# GCN-LABEL: {{^}}name: vop2_64bit
|
|
|
|
|
2017-10-25 02:04:54 +08:00
|
|
|
# GCN: %{{[0-9]+}}:vgpr_32 = V_BCNT_U32_B32_e64 %{{[0-9]+}}, killed %{{[0-9]+}}, implicit-def %vcc, implicit %exec
|
|
|
|
# GCN: %{{[0-9]+}}:vgpr_32 = V_BFM_B32_e64 %{{[0-9]+}}, killed %{{[0-9]+}}, implicit-def %vcc, implicit %exec
|
|
|
|
# GCN: %{{[0-9]+}}:vgpr_32 = V_CVT_PKNORM_I16_F32_e64 0, %{{[0-9]+}}, 0, killed %{{[0-9]+}}, 0, implicit-def %vcc, implicit %exec
|
|
|
|
# GCN: %{{[0-9]+}}:sgpr_32 = V_READLANE_B32 killed %{{[0-9]+}}, 0, implicit-def %vcc, implicit %exec
|
[AMDGPU] SDWA: remove support for VOP2 instructions that have only 64-bit encoding
Summary:
Despite that this instructions are listed in VOP2, they are treated as VOP3 in specs. They should not support SDWA.
There are no real instructions for them, but there are pseudo instructions.
Reviewers: arsenm, vpykhtin, cfang
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34403
llvm-svn: 305999
2017-06-22 20:42:14 +08:00
|
|
|
|
|
|
|
---
|
|
|
|
name: vop2_64bit
|
|
|
|
tracksRegLiveness: true
|
2017-10-25 02:04:54 +08:00
|
|
|
registers:
|
[AMDGPU] SDWA: remove support for VOP2 instructions that have only 64-bit encoding
Summary:
Despite that this instructions are listed in VOP2, they are treated as VOP3 in specs. They should not support SDWA.
There are no real instructions for them, but there are pseudo instructions.
Reviewers: arsenm, vpykhtin, cfang
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34403
llvm-svn: 305999
2017-06-22 20:42:14 +08:00
|
|
|
- { id: 0, class: vreg_64 }
|
|
|
|
- { id: 1, class: vreg_64 }
|
|
|
|
- { id: 2, class: sreg_64 }
|
|
|
|
- { id: 3, class: vgpr_32 }
|
|
|
|
- { id: 4, class: sreg_32_xm0 }
|
|
|
|
- { id: 5, class: sreg_32_xm0 }
|
|
|
|
- { id: 6, class: sreg_32 }
|
|
|
|
- { id: 7, class: sreg_32_xm0 }
|
|
|
|
- { id: 8, class: sreg_32 }
|
|
|
|
- { id: 9, class: vgpr_32 }
|
|
|
|
- { id: 12, class: vgpr_32 }
|
|
|
|
- { id: 13, class: vgpr_32 }
|
|
|
|
- { id: 14, class: vgpr_32 }
|
|
|
|
- { id: 15, class: vgpr_32 }
|
|
|
|
- { id: 16, class: vgpr_32 }
|
|
|
|
- { id: 17, class: vgpr_32 }
|
|
|
|
- { id: 18, class: vgpr_32 }
|
|
|
|
- { id: 19, class: sgpr_32 }
|
|
|
|
- { id: 20, class: vgpr_32 }
|
|
|
|
body: |
|
|
|
|
bb.0:
|
|
|
|
liveins: %vgpr0_vgpr1, %vgpr2_vgpr3, %sgpr30_sgpr31
|
2017-10-25 02:04:54 +08:00
|
|
|
|
[AMDGPU] SDWA: remove support for VOP2 instructions that have only 64-bit encoding
Summary:
Despite that this instructions are listed in VOP2, they are treated as VOP3 in specs. They should not support SDWA.
There are no real instructions for them, but there are pseudo instructions.
Reviewers: arsenm, vpykhtin, cfang
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34403
llvm-svn: 305999
2017-06-22 20:42:14 +08:00
|
|
|
%2 = COPY %sgpr30_sgpr31
|
|
|
|
%1 = COPY %vgpr2_vgpr3
|
|
|
|
%0 = COPY %vgpr0_vgpr1
|
|
|
|
%3 = FLAT_LOAD_DWORD %1, 0, 0, 0, implicit %exec, implicit %flat_scr :: (load 4)
|
|
|
|
|
|
|
|
%12 = V_LSHRREV_B32_e64 16, %3, implicit %exec
|
|
|
|
%13 = V_BCNT_U32_B32_e64 %3, killed %12, implicit-def %vcc, implicit %exec
|
|
|
|
|
|
|
|
%14 = V_LSHRREV_B32_e64 16, %13, implicit %exec
|
|
|
|
%15 = V_BFM_B32_e64 %13, killed %14, implicit-def %vcc, implicit %exec
|
|
|
|
|
|
|
|
%16 = V_LSHRREV_B32_e64 16, %15, implicit %exec
|
2017-07-18 22:23:26 +08:00
|
|
|
%17 = V_CVT_PKNORM_I16_F32_e64 0, %15, 0, killed %16, 0, implicit-def %vcc, implicit %exec
|
[AMDGPU] SDWA: remove support for VOP2 instructions that have only 64-bit encoding
Summary:
Despite that this instructions are listed in VOP2, they are treated as VOP3 in specs. They should not support SDWA.
There are no real instructions for them, but there are pseudo instructions.
Reviewers: arsenm, vpykhtin, cfang
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34403
llvm-svn: 305999
2017-06-22 20:42:14 +08:00
|
|
|
|
|
|
|
%18 = V_LSHRREV_B32_e64 16, %17, implicit %exec
|
|
|
|
%19 = V_READLANE_B32 killed %18, 0, implicit-def %vcc, implicit %exec
|
|
|
|
%20 = V_MOV_B32_e64 %19, implicit %exec
|
|
|
|
|
|
|
|
FLAT_STORE_DWORD %0, %20, 0, 0, 0, implicit %exec, implicit %flat_scr :: (store 4)
|
|
|
|
%sgpr30_sgpr31 = COPY %2
|
|
|
|
S_SETPC_B64_return %sgpr30_sgpr31
|