maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/memory-legalizer-multiple-m...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

66 lines
3.2 KiB
Plaintext
Raw Normal View History

[AMDGPU] Simplify memory legalizer - Make code easier to maintain. - Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM. - Add support to generate waitcnts for LDS and GDS memory. Differential Revision: https://reviews.llvm.org/D47504 llvm-svn: 334241
2018-06-08 06:28:32 +08:00
# RUN: llc -march=amdgcn -mcpu=gfx803 -run-pass si-memory-legalizer %s -o - | FileCheck -check-prefix=GCN %s
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
---
[AMDGPU] Simplify memory legalizer - Make code easier to maintain. - Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM. - Add support to generate waitcnts for LDS and GDS memory. Differential Revision: https://reviews.llvm.org/D47504 llvm-svn: 334241
2018-06-08 06:28:32 +08:00
# GCN-LABEL: name: multiple_mem_operands
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
[AMDGPU] Simplify memory legalizer - Make code easier to maintain. - Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM. - Add support to generate waitcnts for LDS and GDS memory. Differential Revision: https://reviews.llvm.org/D47504 llvm-svn: 334241
2018-06-08 06:28:32 +08:00
# GCN-LABEL: bb.3:
# GCN: S_WAITCNT 3952
# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
# GCN-NEXT: S_WAITCNT 3952
# GCN-NEXT: BUFFER_WBINVL1_VOL
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
name: multiple_mem_operands
body: |
bb.0.entry:
[AMDGPU] Simplify memory legalizer - Make code easier to maintain. - Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM. - Add support to generate waitcnts for LDS and GDS memory. Differential Revision: https://reviews.llvm.org/D47504 llvm-svn: 334241
2018-06-08 06:28:32 +08:00
successors: %bb.1(0x30000000), %bb.2(0x50000000)
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
liveins: $sgpr0_sgpr1, $sgpr3
[AMDGPU] gfx1010 VMEM and SMEM implementation Differential Revision: https://reviews.llvm.org/D61330 llvm-svn: 359621
2019-05-01 06:08:23 +08:00
$sgpr2 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 44, 0, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
$sgpr8 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
[AMDGPU] gfx1010 VMEM and SMEM implementation Differential Revision: https://reviews.llvm.org/D61330 llvm-svn: 359621
2019-05-01 06:08:23 +08:00
$sgpr4_sgpr5 = S_LOAD_DWORDX2_IMM $sgpr0_sgpr1, 36, 0, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(4)* undef`)
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
$sgpr9 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
$sgpr10 = S_MOV_B32 4294967295, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
$sgpr11 = S_MOV_B32 15204352, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
$vgpr0 = V_MOV_B32_e32 1, implicit $exec
[AMDGPU] Extend buffer intrinsics with swizzling Summary: Extend cachepolicy operand in the new VMEM buffer intrinsics to supply information whether the buffer data is swizzled. Also, propagate this information to MIR. Intrinsics updated: int_amdgcn_raw_buffer_load int_amdgcn_raw_buffer_load_format int_amdgcn_raw_buffer_store int_amdgcn_raw_buffer_store_format int_amdgcn_raw_tbuffer_load int_amdgcn_raw_tbuffer_store int_amdgcn_struct_buffer_load int_amdgcn_struct_buffer_load_format int_amdgcn_struct_buffer_store int_amdgcn_struct_buffer_store_format int_amdgcn_struct_tbuffer_load int_amdgcn_struct_tbuffer_store Furthermore, disable merging of VMEM buffer instructions in SI Load/Store optimizer, if the "swizzled" bit on the instruction is on. The default value of the bit is 0, meaning that data in buffer is linear and buffer instructions can be merged. There is no difference in the generated code with this commit. However, in the future it will be expected that front-ends use buffer intrinsics with correct "swizzled" bit set. Reviewers: arsenm, nhaehnle, tpr Reviewed By: nhaehnle Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, arphaman, jfb, Petar.Avramovic, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68200 llvm-svn: 373491
2019-10-03 01:22:36 +08:00
BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into `i32 addrspace(5)* undef`)
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
S_WAITCNT 127
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
S_CMP_LG_U32 killed $sgpr2, 0, implicit-def $scc
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
S_WAITCNT 3855
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
$vgpr0 = V_MOV_B32_e32 2, implicit $exec
$vgpr1 = V_MOV_B32_e32 32772, implicit $exec
[AMDGPU] Extend buffer intrinsics with swizzling Summary: Extend cachepolicy operand in the new VMEM buffer intrinsics to supply information whether the buffer data is swizzled. Also, propagate this information to MIR. Intrinsics updated: int_amdgcn_raw_buffer_load int_amdgcn_raw_buffer_load_format int_amdgcn_raw_buffer_store int_amdgcn_raw_buffer_store_format int_amdgcn_raw_tbuffer_load int_amdgcn_raw_tbuffer_store int_amdgcn_struct_buffer_load int_amdgcn_struct_buffer_load_format int_amdgcn_struct_buffer_store int_amdgcn_struct_buffer_store_format int_amdgcn_struct_tbuffer_load int_amdgcn_struct_tbuffer_store Furthermore, disable merging of VMEM buffer instructions in SI Load/Store optimizer, if the "swizzled" bit on the instruction is on. The default value of the bit is 0, meaning that data in buffer is linear and buffer instructions can be merged. There is no difference in the generated code with this commit. However, in the future it will be expected that front-ends use buffer intrinsics with correct "swizzled" bit set. Reviewers: arsenm, nhaehnle, tpr Reviewed By: nhaehnle Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, arphaman, jfb, Petar.Avramovic, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68200 llvm-svn: 373491
2019-10-03 01:22:36 +08:00
BUFFER_STORE_DWORD_OFFEN killed $vgpr0, killed $vgpr1, $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into `i32 addrspace(5)* undef`)
[AMDGPU] Simplify memory legalizer - Make code easier to maintain. - Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM. - Add support to generate waitcnts for LDS and GDS memory. Differential Revision: https://reviews.llvm.org/D47504 llvm-svn: 334241
2018-06-08 06:28:32 +08:00
S_CBRANCH_SCC0 %bb.1, implicit killed $scc
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
[AMDGPU] Simplify memory legalizer - Make code easier to maintain. - Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM. - Add support to generate waitcnts for LDS and GDS memory. Differential Revision: https://reviews.llvm.org/D47504 llvm-svn: 334241
2018-06-08 06:28:32 +08:00
bb.2:
successors: %bb.3(0x80000000)
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
liveins: $sgpr0_sgpr1, $sgpr4_sgpr5, $sgpr3, $sgpr8_sgpr9_sgpr10_sgpr11
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
[AMDGPU] gfx1010 VMEM and SMEM implementation Differential Revision: https://reviews.llvm.org/D61330 llvm-svn: 359621
2019-05-01 06:08:23 +08:00
$sgpr0 = S_LOAD_DWORD_IMM killed $sgpr0_sgpr1, 52, 0, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
S_WAITCNT 3855
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
$vgpr0 = V_MOV_B32_e32 32772, implicit $exec
[AMDGPU] Simplify memory legalizer - Make code easier to maintain. - Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM. - Add support to generate waitcnts for LDS and GDS memory. Differential Revision: https://reviews.llvm.org/D47504 llvm-svn: 334241
2018-06-08 06:28:32 +08:00
S_BRANCH %bb.3
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
[AMDGPU] Simplify memory legalizer - Make code easier to maintain. - Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM. - Add support to generate waitcnts for LDS and GDS memory. Differential Revision: https://reviews.llvm.org/D47504 llvm-svn: 334241
2018-06-08 06:28:32 +08:00
bb.1:
successors: %bb.3(0x80000000)
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
liveins: $sgpr0_sgpr1, $sgpr4_sgpr5, $sgpr3, $sgpr8_sgpr9_sgpr10_sgpr11
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
[AMDGPU] gfx1010 VMEM and SMEM implementation Differential Revision: https://reviews.llvm.org/D61330 llvm-svn: 359621
2019-05-01 06:08:23 +08:00
$sgpr0 = S_LOAD_DWORD_IMM killed $sgpr0_sgpr1, 48, 0, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
S_WAITCNT 3855
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
$vgpr0 = V_MOV_B32_e32 4, implicit $exec
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
[AMDGPU] Simplify memory legalizer - Make code easier to maintain. - Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM. - Add support to generate waitcnts for LDS and GDS memory. Differential Revision: https://reviews.llvm.org/D47504 llvm-svn: 334241
2018-06-08 06:28:32 +08:00
bb.3:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
liveins: $sgpr3, $sgpr4_sgpr5, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0, $sgpr0
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
S_WAITCNT 127
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
$sgpr0 = S_LSHL_B32 killed $sgpr0, 2, implicit-def dead $scc
AMDGPU: Rename add/sub with carry out instructions 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).
2020-07-14 21:18:36 +08:00
$vgpr0 = V_ADD_CO_U32_e32 killed $sgpr0, killed $vgpr0, implicit-def dead $vcc, implicit $exec
[AMDGPU] Extend buffer intrinsics with swizzling Summary: Extend cachepolicy operand in the new VMEM buffer intrinsics to supply information whether the buffer data is swizzled. Also, propagate this information to MIR. Intrinsics updated: int_amdgcn_raw_buffer_load int_amdgcn_raw_buffer_load_format int_amdgcn_raw_buffer_store int_amdgcn_raw_buffer_store_format int_amdgcn_raw_tbuffer_load int_amdgcn_raw_tbuffer_store int_amdgcn_struct_buffer_load int_amdgcn_struct_buffer_load_format int_amdgcn_struct_buffer_store int_amdgcn_struct_buffer_store_format int_amdgcn_struct_tbuffer_load int_amdgcn_struct_tbuffer_store Furthermore, disable merging of VMEM buffer instructions in SI Load/Store optimizer, if the "swizzled" bit on the instruction is on. The default value of the bit is 0, meaning that data in buffer is linear and buffer instructions can be merged. There is no difference in the generated code with this commit. However, in the future it will be expected that front-ends use buffer intrinsics with correct "swizzled" bit set. Reviewers: arsenm, nhaehnle, tpr Reviewed By: nhaehnle Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, arphaman, jfb, Petar.Avramovic, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68200 llvm-svn: 373491
2019-10-03 01:22:36 +08:00
$vgpr0 = BUFFER_LOAD_DWORD_OFFEN killed $vgpr0, killed $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 0, 0, 0, 0, 0, 0, implicit $exec :: (load syncscope("agent-one-as") unordered 4 from `i32 addrspace(1)* undef`), (load syncscope("workgroup-one-as") seq_cst 4 from `[8192 x i32] addrspace(5)* undef`)
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
$vgpr1 = V_MOV_B32_e32 $sgpr4, implicit $exec, implicit-def $vgpr1_vgpr2, implicit $sgpr4_sgpr5
$vgpr2 = V_MOV_B32_e32 killed $sgpr5, implicit $exec, implicit $sgpr4_sgpr5, implicit $exec
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
S_WAITCNT 3952
[AMDGPU] gfx1010 VMEM and SMEM implementation Differential Revision: https://reviews.llvm.org/D61330 llvm-svn: 359621
2019-05-01 06:08:23 +08:00
FLAT_STORE_DWORD killed $vgpr1_vgpr2, killed $vgpr0, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into `i32 addrspace(1)* undef`)
[AMDGPU] Add support for immediate operand for S_ENDPGM Summary: Add support for immediate operand in S_ENDPGM Change-Id: I0c56a076a10980f719fb2a8f16407e9c301013f6 Reviewers: alexshap Subscribers: qcolombet, arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, tpr, t-tye, eraman, arphaman, Petar.Avramovic, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D59213 llvm-svn: 355902
2019-03-12 17:52:58 +08:00
S_ENDPGM 0
AMDGPU: Handle more than one memory operand in SIMemoryLegalizer Differential Revision: https://reviews.llvm.org/D37397 llvm-svn: 312725
2017-09-08 00:14:21 +08:00
...