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

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

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@362127 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/SIFormMemoryClauses.cpp b/lib/Target/AMDGPU/SIFormMemoryClauses.cpp
index 2cbed99beb2ffe19168f4993bd4f0362675a9b7d..f3c9ad63a80aba5da5575b773766c815ce33f64f 100644 (file)
--- a/lib/Target/AMDGPU/SIFormMemoryClauses.cpp
+++ b/lib/Target/AMDGPU/SIFormMemoryClauses.cpp
@@ -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;
 

diff --git a/test/CodeGen/AMDGPU/disable_form_clauses.ll b/test/CodeGen/AMDGPU/disable_form_clauses.ll
new file mode 100644 (file)
index 0000000..dd6f03f
--- /dev/null
+++ b/test/CodeGen/AMDGPU/disable_form_clauses.ll
@@ -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" }
+