RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
Code Issues Projects Releases Wiki Activity

[AMDGPU] Added target-specific attribute amdgpu-max-memory-clause

Browse Source 
With LLPC, previous investigation has suggested that si-scheduler
interacts badly with SiFormMemoryClauses on an XNACK target in some
games.

That needs further investigation in the future. In the meantime, this
commit adds a target-specific attribute to allow us to disable
SIFormMemoryClauses by setting it to 1 on a per-function basis for LLPC
to use.

Differential Revision: https://reviews.llvm.org/D62572

Change-Id: Ia0ca12ce79093cbbe86caded723ffb13384ede92
llvm-svn: 362127
This commit is contained in:
Tim Renouf 2019-05-30 18:46:34 +00:00
parent 52d7ce51cc
commit 96b45bff23
2 changed files with 68 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/Target/AMDGPU/SIFormMemoryClauses.cpp
View File

@ -319,6 +319,8 @@ bool SIFormMemoryClauses::runOnMachineFunction(MachineFunction &MF) {
MaxVGPRs = TRI->getAllocatableSet(MF, &AMDGPU::VGPR_32RegClass).count();
MaxSGPRs = TRI->getAllocatableSet(MF, &AMDGPU::SGPR_32RegClass).count();
unsigned FuncMaxClause = AMDGPU::getIntegerAttribute(
MF.getFunction(), "amdgpu-max-memory-clause", MaxClause);
for (MachineBasicBlock &MBB : MF) {
MachineBasicBlock::instr_iterator Next;
@ -339,7 +341,7 @@ bool SIFormMemoryClauses::runOnMachineFunction(MachineFunction &MF) {
continue;
unsigned Length = 1;
for ( ; Next != E && Length < MaxClause; ++Next) {
for ( ; Next != E && Length < FuncMaxClause; ++Next) {
if (!isValidClauseInst(*Next, IsVMEM))
break;

65
test/CodeGen/AMDGPU/disable_form_clauses.ll Normal file
View File

@ -0,0 +1,65 @@
; RUN: llc -march=amdgcn -mcpu=gfx902 -verify-machineinstrs -amdgpu-enable-global-sgpr-addr -stop-after=si-form-memory-clauses < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}name:{{[ ]*}}vector_clause
; GCN: BUNDLE
; GCN-NEXT: LOAD_DWORDX2
; GCN-NEXT: LOAD_DWORDX2
; GCN-NEXT: {{^ *[}]}}
define amdgpu_kernel void @vector_clause(<4 x i32> addrspace(1)* noalias nocapture readonly %arg, <4 x i32> addrspace(1)* noalias nocapture %arg1) {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp2 = zext i32 %tmp to i64
%tmp3 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp2
%tmp4 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp3, align 16
%tmp5 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp2
%tmp6 = add nuw nsw i64 %tmp2, 1
%tmp7 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp6
%tmp8 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp7, align 16
%tmp9 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp6
%tmp10 = add nuw nsw i64 %tmp2, 2
%tmp11 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp10
%tmp12 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp11, align 16
%tmp13 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp10
%tmp14 = add nuw nsw i64 %tmp2, 3
%tmp15 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp14
%tmp16 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp15, align 16
%tmp17 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp14
store <4 x i32> %tmp4, <4 x i32> addrspace(1)* %tmp5, align 16
store <4 x i32> %tmp8, <4 x i32> addrspace(1)* %tmp9, align 16
store <4 x i32> %tmp12, <4 x i32> addrspace(1)* %tmp13, align 16
store <4 x i32> %tmp16, <4 x i32> addrspace(1)* %tmp17, align 16
ret void
}
; GCN-LABEL: {{^}}name:{{[ ]*}}no_vector_clause
; GCN-NOT: BUNDLE
define amdgpu_kernel void @no_vector_clause(<4 x i32> addrspace(1)* noalias nocapture readonly %arg, <4 x i32> addrspace(1)* noalias nocapture %arg1) #0 {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp2 = zext i32 %tmp to i64
%tmp3 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp2
%tmp4 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp3, align 16
%tmp5 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp2
%tmp6 = add nuw nsw i64 %tmp2, 1
%tmp7 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp6
%tmp8 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp7, align 16
%tmp9 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp6
%tmp10 = add nuw nsw i64 %tmp2, 2
%tmp11 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp10
%tmp12 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp11, align 16
%tmp13 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp10
%tmp14 = add nuw nsw i64 %tmp2, 3
%tmp15 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp14
%tmp16 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp15, align 16
%tmp17 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp14
store <4 x i32> %tmp4, <4 x i32> addrspace(1)* %tmp5, align 16
store <4 x i32> %tmp8, <4 x i32> addrspace(1)* %tmp9, align 16
store <4 x i32> %tmp12, <4 x i32> addrspace(1)* %tmp13, align 16
store <4 x i32> %tmp16, <4 x i32> addrspace(1)* %tmp17, align 16
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x()
attributes #0 = { "amdgpu-max-memory-clause"="1" }