1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
llvm-mirror/test/CodeGen/AMDGPU/waitcnt-loop-irreducible.mir
Piotr Sobczak b9148f5d85 [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
2019-10-02 17:22:36 +00:00

104 lines
2.8 KiB
YAML

# RUN: llc -march=amdgcn -mcpu=gfx803 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefixes=GCN,GFX8 %s
# RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefixes=GCN,GFX9 %s
--- |
define amdgpu_ps void @irreducible_loop() {
ret void
}
define amdgpu_ps void @irreducible_loop_extended() {
ret void
}
...
---
# GCN-LABEL: name: irreducible_loop{{$}}
# GCN: S_LOAD_DWORDX4_IMM
# GFX8: S_WAITCNT 127{{$}}
# GFX9: S_WAITCNT 49279{{$}}
# GCN: S_BUFFER_LOAD_DWORD_IMM
# GFX8: S_WAITCNT 127{{$}}
# GFX9: S_WAITCNT 49279{{$}}
# GCN: S_CMP_GE_I32
name: irreducible_loop
body: |
bb.0:
successors: %bb.3, %bb.2
S_CBRANCH_VCCZ %bb.2, implicit $vcc
S_BRANCH %bb.3
bb.1:
successors: %bb.3, %bb.2
S_CBRANCH_VCCNZ %bb.3, implicit $vcc
bb.2:
successors: %bb.3
renamable $sgpr4_sgpr5_sgpr6_sgpr7 = S_LOAD_DWORDX4_IMM renamable $sgpr0_sgpr1, 0, 0, 0
renamable $sgpr3 = S_BUFFER_LOAD_DWORD_IMM killed renamable $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0
bb.3:
successors: %bb.1, %bb.4
S_CMP_GE_I32 renamable $sgpr2, renamable $sgpr3, implicit-def $scc
S_CBRANCH_SCC0 %bb.1, implicit killed $scc
bb.4:
S_ENDPGM 0
...
# GCN-LABEL: name: irreducible_loop_extended
# GCN: S_LOAD_DWORDX4_IMM
# GFX8: S_WAITCNT 127{{$}}
# GFX9: S_WAITCNT 49279{{$}}
# GCN: BUFFER_STORE_DWORD_OFFEN_exact
# GFX8: S_WAITCNT 127{{$}}
# GFX9: S_WAITCNT 49279{{$}}
# GCN: BUFFER_STORE_DWORD_OFFEN_exact
# GCN: S_LOAD_DWORDX4_IMM
# GFX8: S_WAITCNT 127{{$}}
# GFX9: S_WAITCNT 49279{{$}}
# GCN: BUFFER_ATOMIC_ADD_OFFSET_RTN
# GCN: S_WAITCNT 3952
# GCN: FLAT_STORE_DWORD
# GCN: S_ENDPGM 0
name: irreducible_loop_extended
body: |
bb.0:
successors: %bb.1, %bb.2
$sgpr4_sgpr5_sgpr6_sgpr7 = S_LOAD_DWORDX4_IMM renamable $sgpr2_sgpr3, 0, 0, 0
S_CBRANCH_VCCZ %bb.2, implicit $vcc
bb.1:
successors: %bb.2
BUFFER_STORE_DWORD_OFFEN_exact killed renamable $vgpr3, renamable $vgpr2, renamable $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, 0, 0, implicit $exec
bb.2:
successors: %bb.3, %bb.6
S_CBRANCH_VCCNZ %bb.6, implicit $vcc
bb.3:
successors: %bb.4, %bb.5
BUFFER_STORE_DWORD_OFFEN_exact killed renamable $vgpr3, killed renamable $vgpr2, killed renamable $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, 0, 0, implicit $exec
S_CBRANCH_VCCNZ %bb.5, implicit $vcc
bb.4:
successors: %bb.5
renamable $sgpr12_sgpr13_sgpr14_sgpr15 = S_LOAD_DWORDX4_IMM killed renamable $sgpr2_sgpr3, 64, 0, 0
renamable $vgpr2 = BUFFER_ATOMIC_ADD_OFFSET_RTN killed renamable $vgpr2, killed renamable $sgpr12_sgpr13_sgpr14_sgpr15, 0, 0, 0, implicit $exec
bb.5:
successors: %bb.6
bb.6:
FLAT_STORE_DWORD $vgpr3_vgpr4, $vgpr2, 0, 0, 0, 0, implicit $exec, implicit $flat_scr
S_ENDPGM 0
...