maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] Supported ds_write_b128 generation. 

Summary: This is a follow-on patch of https://reviews.llvm.org/D44210

Author: FarhanaAleen

Reviewed By: msearles

Subscribers: llvm-commits, AMDGPU

Differential Revision: https://reviews.llvm.org/D44319

llvm-svn: 327726
This commit is contained in:
Farhana Aleen 2018-03-16 18:12:00 +00:00
parent c9977f3877
commit c6c9dc8773
10 changed files with 59 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
View File

@ -383,6 +383,9 @@ def store_align8_local : Aligned8Bytes <
(ops node:$val, node:$ptr), (store_local node:$val, node:$ptr)
>;
def store_align16_local : Aligned16Bytes <
(ops node:$val, node:$ptr), (store_local node:$val, node:$ptr)
>;
def load_flat : FlatLoad <load>;
def az_extloadi8_flat : FlatLoad <az_extloadi8>;

2
llvm/lib/Target/AMDGPU/DSInstructions.td
View File

@ -719,6 +719,8 @@ def : DS64Bit4ByteAlignedWritePat<DS_WRITE2_B32_gfx9, store_local>;
let AddedComplexity = 100 in {
defm : DSWritePat_mc <DS_WRITE_B64, v2i32, "store_align8_local">;
defm : DSWritePat_mc <DS_WRITE_B128, v4i32, "store_align16_local">;
} // End AddedComplexity = 100
class DSAtomicRetPat<DS_Pseudo inst, ValueType vt, PatFrag frag> : GCNPat <
(frag (DS1Addr1Offset i32:$ptr, i32:$offset), vt:$value),

12
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
View File

@ -5833,14 +5833,14 @@ SDValue SITargetLowering::LowerSTORE(SDValue Op, SelectionDAG &DAG) const {
llvm_unreachable("unsupported private_element_size");
}
} else if (AS == AMDGPUASI.LOCAL_ADDRESS) {
// Use ds_write_b128 if possible.
if (Subtarget->useDS128(EnableDS128) && Store->getAlignment() >= 16 &&
VT.getStoreSize() == 16)
return SDValue();
if (NumElements > 2)
return SplitVectorStore(Op, DAG);
if (NumElements == 2)
return Op;
// If properly aligned, if we split we might be able to use ds_write_b64.
return SplitVectorStore(Op, DAG);
return SDValue();
} else {
llvm_unreachable("unhandled address space");
}

5
llvm/lib/Target/AMDGPU/SIInstrInfo.td
View File

@ -457,11 +457,16 @@ def store_glue_align8 : Aligned8Bytes <
(ops node:$value, node:$ptr), (store_glue node:$value, node:$ptr)
>;
def store_glue_align16 : Aligned16Bytes <
(ops node:$value, node:$ptr), (store_glue node:$value, node:$ptr)
>;
def store_local_m0 : StoreFrag<store_glue>, LocalAddress;
def truncstorei8_local_m0 : StoreFrag<truncstorei8_glue>, LocalAddress;
def truncstorei16_local_m0 : StoreFrag<truncstorei16_glue>, LocalAddress;
def store_align8_local_m0 : StoreFrag<store_glue_align8>, LocalAddress;
def store_align16_local_m0 : StoreFrag<store_glue_align16>, LocalAddress;
def si_setcc_uniform : PatFrag <
(ops node:$lhs, node:$rhs, node:$cond),

11
llvm/test/CodeGen/AMDGPU/load-local-f32.ll
View File

@ -2,7 +2,7 @@
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefixes=EG,FUNC %s
; Testing for ds_read_128
; Testing for ds_read/write_128
; RUN: llc -march=amdgcn -mcpu=tahiti -amdgpu-ds128 < %s | FileCheck -check-prefixes=SI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
@ -127,17 +127,22 @@ entry:
ret void
}
; Tests if ds_read_b128 gets generated for the 16 byte aligned load.
; Tests if ds_read/write_b128 gets generated for the 16 byte aligned load.
; FUNC-LABEL: {{^}}local_v4f32_to_128:
; SI-NOT: ds_read_b128
; SI-NOT: ds_write_b128
; CIVI: ds_read_b128
; CIVI: ds_write_b128
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_v4f32_to_128(<4 x float> addrspace(3)* %out, <4 x float> addrspace(3)* %in) {
%ld = load <4 x float>, <4 x float> addrspace(3)* %in, align 16
store <4 x float> %ld, <4 x float> addrspace(3)* %out
store <4 x float> %ld, <4 x float> addrspace(3)* %out, align 16
ret void
}

5
llvm/test/CodeGen/AMDGPU/load-local-f64.ll
View File

@ -176,7 +176,10 @@ entry:
; Tests if ds_read_b128 gets generated for the 16 byte aligned load.
; FUNC-LABEL: {{^}}local_load_v2f64_to_128:
; CIVI: ds_read_b128
; CIVI: ds_write_b128
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
@ -184,7 +187,7 @@ entry:
define amdgpu_kernel void @local_load_v2f64_to_128(<2 x double> addrspace(3)* %out, <2 x double> addrspace(3)* %in) {
entry:
%ld = load <2 x double>, <2 x double> addrspace(3)* %in, align 16
store <2 x double> %ld, <2 x double> addrspace(3)* %out
store <2 x double> %ld, <2 x double> addrspace(3)* %out, align 16
ret void
}

11
llvm/test/CodeGen/AMDGPU/load-local-i16.ll
View File

@ -3,7 +3,7 @@
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,GFX89,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
; Testing for ds_read_b128
; Testing for ds_read/write_b128
; RUN: llc -march=amdgcn -mcpu=tonga -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
@ -939,17 +939,22 @@ define amdgpu_kernel void @local_sextload_v32i16_to_v32i64(<32 x i64> addrspace(
; ret void
; }
; Tests if ds_read_b128 gets generated for the 16 byte aligned load.
; Tests if ds_read/write_b128 gets generated for the 16 byte aligned load.
; FUNC-LABEL: {{^}}local_v8i16_to_128:
; SI-NOT: ds_read_b128
; SI-NOT: ds_write_b128
; CIVI: ds_read_b128
; CIVI: ds_write_b128
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_v8i16_to_128(<8 x i16> addrspace(3)* %out, <8 x i16> addrspace(3)* %in) {
%ld = load <8 x i16>, <8 x i16> addrspace(3)* %in, align 16
store <8 x i16> %ld, <8 x i16> addrspace(3)* %out
store <8 x i16> %ld, <8 x i16> addrspace(3)* %out, align 16
ret void
}

11
llvm/test/CodeGen/AMDGPU/load-local-i32.ll
View File

@ -3,7 +3,7 @@
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,VI,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
; Testing for ds_read_128
; Testing for ds_read/write_128
; RUN: llc -march=amdgcn -mcpu=tahiti -amdgpu-ds128 < %s | FileCheck -check-prefixes=SI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
@ -180,17 +180,22 @@ define amdgpu_kernel void @local_sextload_v4i32_to_v4i64(<4 x i64> addrspace(3)*
ret void
}
; Tests if ds_read_b128 gets generated for the 16 byte aligned load.
; Tests if ds_read/write_b128 gets generated for the 16 byte aligned load.
; FUNC-LABEL: {{^}}local_v4i32_to_128:
; SI-NOT: ds_read_b128
; SI-NOT: ds_write_b128
; CIVI: ds_read_b128
; CIVI: ds_write_b128
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_v4i32_to_128(<4 x i32> addrspace(3)* %out, <4 x i32> addrspace(3)* %in) {
%ld = load <4 x i32>, <4 x i32> addrspace(3)* %in, align 16
store <4 x i32> %ld, <4 x i32> addrspace(3)* %out
store <4 x i32> %ld, <4 x i32> addrspace(3)* %out, align 16
ret void
}

11
llvm/test/CodeGen/AMDGPU/load-local-i64.ll
View File

@ -4,7 +4,7 @@
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefixes=EG,FUNC %s
; Testing for ds_read_b128
; Testing for ds_read/write_b128
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
@ -40,13 +40,16 @@ entry:
ret void
}
; Tests if ds_read_b128 gets generated for the 16 byte aligned load.
; Tests if ds_read/write_b128 gets generated for the 16 byte aligned load.
; FUNC-LABEL: {{^}}local_load_v2i64_to_128:
; CIVI: ds_read_b128
; CIVI: ds_write_b128
define amdgpu_kernel void @local_load_v2i64_to_128(<2 x i64> addrspace(3)* %out, <2 x i64> addrspace(3)* %in) {
entry:
%ld = load <2 x i64>, <2 x i64> addrspace(3)* %in
store <2 x i64> %ld, <2 x i64> addrspace(3)* %out
%ld = load <2 x i64>, <2 x i64> addrspace(3)* %in, align 16
store <2 x i64> %ld, <2 x i64> addrspace(3)* %out, align 16
ret void
}

11
llvm/test/CodeGen/AMDGPU/load-local-i8.ll
View File

@ -3,7 +3,7 @@
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
; RUN: llc -march=r600 -mtriple=r600---amdgiz -mcpu=redwood -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
; Testing for ds_read_b128
; Testing for ds_read/write_b128
; RUN: llc -march=amdgcn -mcpu=tonga -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
@ -1024,17 +1024,22 @@ define amdgpu_kernel void @local_sextload_v32i8_to_v32i16(<32 x i16> addrspace(3
; ret void
; }
; Tests if ds_read_b128 gets generated for the 16 byte aligned load.
; Tests if ds_read/write_b128 gets generated for the 16 byte aligned load.
; FUNC-LABEL: {{^}}local_v16i8_to_128:
; SI-NOT: ds_read_b128
; SI-NOT: ds_write_b128
; CIVI: ds_read_b128
; CIVI: ds_write_b128
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_v16i8_to_128(<16 x i8> addrspace(3)* %out, <16 x i8> addrspace(3)* %in) {
%ld = load <16 x i8>, <16 x i8> addrspace(3)* %in, align 16
store <16 x i8> %ld, <16 x i8> addrspace(3)* %out
store <16 x i8> %ld, <16 x i8> addrspace(3)* %out, align 16
ret void
}