[PATCH] D37502: [AMDGPU] Fix shouldClusterMemOps to process flat loads

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec created this revision.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, kzhuravl.

Flat loads do not have vdata operand but have vdst instead.


https://reviews.llvm.org/D37502

Files:
  lib/Target/AMDGPU/SIInstrInfo.cpp
  test/CodeGen/AMDGPU/cluster-flat-loads.mir


Index: test/CodeGen/AMDGPU/cluster-flat-loads.mir
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/cluster-flat-loads.mir
@@ -0,0 +1,20 @@
+# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass machine-scheduler %s -o - | FileCheck -check-prefix=GCN %s
+
+# GCN-LABEL: name: cluster_flat_loads
+# GCN:      FLAT_LOAD_DWORD %0, 0
+# GCN-NEXT: FLAT_LOAD_DWORD %0, 4
+# GCN-NEXT: V_ADD_F32_e64
+name: cluster_flat_loads
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vgpr_32 }
+  - { id: 2, class: vgpr_32 }
+  - { id: 3, class: vgpr_32 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1 = FLAT_LOAD_DWORD %0, 0, 0, 0, implicit %exec, implicit %flat_scr :: (load 4)
+    %2 = V_ADD_F32_e64 0, killed %1, 0, 1, 0, 0, implicit %exec
+    %3 = FLAT_LOAD_DWORD %0, 4, 0, 0, implicit %exec, implicit %flat_scr :: (load 4)
+...
Index: lib/Target/AMDGPU/SIInstrInfo.cpp
===================================================================
--- lib/Target/AMDGPU/SIInstrInfo.cpp
+++ lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -366,7 +366,11 @@
       (isMTBUF(FirstLdSt) && isMTBUF(SecondLdSt)) ||
       (isFLAT(FirstLdSt) && isFLAT(SecondLdSt))) {
     FirstDst = getNamedOperand(FirstLdSt, AMDGPU::OpName::vdata);
+    if (!FirstDst)
+      FirstDst = getNamedOperand(FirstLdSt, AMDGPU::OpName::vdst);
     SecondDst = getNamedOperand(SecondLdSt, AMDGPU::OpName::vdata);
+    if (!SecondDst)
+      SecondDst = getNamedOperand(SecondLdSt, AMDGPU::OpName::vdst);
   } else if (isSMRD(FirstLdSt) && isSMRD(SecondLdSt)) {
     FirstDst = getNamedOperand(FirstLdSt, AMDGPU::OpName::sdst);
     SecondDst = getNamedOperand(SecondLdSt, AMDGPU::OpName::sdst);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D37502.113954.patch
Type: text/x-patch
Size: 1742 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170906/84b02515/attachment.bin>