[llvm] 46db606 - AMDGPU: Avoid folding 2 constant operands into an SALU operation

[David Stuttard via llvm-commits]

Author: David Stuttard
Date: 2019-12-04T10:25:34Z
New Revision: 46db60683422180688bff0737142c343ba28e7cb

URL: https://github.com/llvm/llvm-project/commit/46db60683422180688bff0737142c343ba28e7cb
DIFF: https://github.com/llvm/llvm-project/commit/46db60683422180688bff0737142c343ba28e7cb.diff

LOG: AMDGPU: Avoid folding 2 constant operands into an SALU operation

Summary:
Catch the (admittedly unusual) case where SIFoldOperands attempts to fold 2
constant operands into the same SALU operation, with neither operand able to be
encoded as an inline constant.

Change-Id: Ibc48d662c9ffd8bbacd154976b0b1c257ace0927

Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, tpr, t-tye, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D70896

Added: 
    llvm/test/CodeGen/AMDGPU/fold-sgpr-multi-imm.mir

Modified: 
    llvm/lib/Target/AMDGPU/SIFoldOperands.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
index ca17ba8b7229..f2c00ddce94c 100644
--- a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -429,6 +429,29 @@ static bool tryAddToFoldList(SmallVectorImpl<FoldCandidate> &FoldList,
     return true;
   }
 
+  // Check the case where we might introduce a second constant operand to a
+  // scalar instruction
+  if (TII->isSALU(MI->getOpcode())) {
+    const MCInstrDesc &InstDesc = MI->getDesc();
+    const MCOperandInfo &OpInfo = InstDesc.OpInfo[OpNo];
+    const SIRegisterInfo &SRI = TII->getRegisterInfo();
+
+    // Fine if the operand can be encoded as an inline constant
+    if (OpToFold->isImm()) {
+      if (!SRI.opCanUseInlineConstant(OpInfo.OperandType) ||
+          !TII->isInlineConstant(*OpToFold, OpInfo)) {
+        // Otherwise check for another constant
+        for (unsigned i = 0, e = InstDesc.getNumOperands(); i != e; ++i) {
+          auto &Op = MI->getOperand(i);
+          if (OpNo != i &&
+              TII->isLiteralConstantLike(Op, OpInfo)) {
+            return false;
+          }
+        }
+      }
+    }
+  }
+
   appendFoldCandidate(FoldList, MI, OpNo, OpToFold);
   return true;
 }

diff  --git a/llvm/test/CodeGen/AMDGPU/fold-sgpr-multi-imm.mir b/llvm/test/CodeGen/AMDGPU/fold-sgpr-multi-imm.mir
new file mode 100644
index 000000000000..754536577fae
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/fold-sgpr-multi-imm.mir
@@ -0,0 +1,71 @@
+# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-fold-operands %s -o - | FileCheck -check-prefix=GCN %s
+
+# GCN-LABEL: name: test_part_fold{{$}}
+# GCN: %2:sreg_32 = S_ADD_I32 70, %1
+---
+name: test_part_fold
+tracksRegLiveness: true
+body: |
+  bb.0:
+    %0:sreg_32 = S_MOV_B32 70
+    %1:sreg_32 = S_MOV_B32 80
+    %2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
+...
+
+# GCN-LABEL: name: test_inline_const{{$}}
+# GCN: %2:sreg_32 = S_ADD_I32 70, 63
+---
+name: test_inline_const
+tracksRegLiveness: true
+body: |
+  bb.0:
+    %0:sreg_32 = S_MOV_B32 70
+    %1:sreg_32 = S_MOV_B32 63
+    %2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
+...
+# GCN-LABEL: name: test_obscure{{$}}
+# GCN: %2:sreg_32 = S_LSHL2_ADD_U32 70, %1
+---
+name: test_obscure
+tracksRegLiveness: true
+body: |
+  bb.0:
+    %0:sreg_32 = S_MOV_B32 70
+    %1:sreg_32 = S_MOV_B32 80
+    %2:sreg_32 = S_LSHL2_ADD_U32 %0, %1, implicit-def $scc
+...
+# GCN-LABEL: name: test_obscure_inline{{$}}
+# GCN: %2:sreg_32 = S_LSHL2_ADD_U32 70, 63
+---
+name: test_obscure_inline
+tracksRegLiveness: true
+body: |
+  bb.0:
+    %0:sreg_32 = S_MOV_B32 70
+    %1:sreg_32 = S_MOV_B32 63
+    %2:sreg_32 = S_LSHL2_ADD_U32 %0, %1, implicit-def $scc
+...
+# GCN-LABEL: name: test_frameindex{{$}}
+# GCN: %1:sreg_32 = S_ADD_I32 %stack.0, %0
+---
+name: test_frameindex
+tracksRegLiveness: true
+stack:
+  - { id: 0, type: default, offset: 0, size: 64, alignment: 16}
+body: |
+  bb.0:
+    %0:sreg_32 = S_MOV_B32 70
+    %1:sreg_32 = S_ADD_I32 %stack.0, %0, implicit-def $scc
+...
+# GCN-LABEL: name: test_frameindex_inline{{$}}
+# GCN: %1:sreg_32 = S_ADD_I32 %stack.0, 63
+---
+name: test_frameindex_inline
+tracksRegLiveness: true
+stack:
+  - { id: 0, type: default, offset: 0, size: 64, alignment: 16}
+body: |
+  bb.0:
+    %0:sreg_32 = S_MOV_B32 63
+    %1:sreg_32 = S_ADD_I32 %stack.0, %0, implicit-def $scc
+...