[AMDGPU] Allow tied operand subreg folding

Turns out it makes sense, contrarily to what comment said.

Differential Revision: https://reviews.llvm.org/D69287

diff --git a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
index 4eac031..69ac367 100644 (file)
--- a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -513,18 +513,6 @@ void SIFoldOperands::foldOperand(
   if (UseOp.isReg() && OpToFold.isReg()) {
     if (UseOp.isImplicit() || UseOp.getSubReg() != AMDGPU::NoSubRegister)
       return;
-
-    // Don't fold subregister extracts into tied operands, only if it is a full
-    // copy since a subregister use tied to a full register def doesn't really
-    // make sense. e.g. don't fold:
-    //
-    // %1 = COPY %0:sub1
-    // %2<tied3> = V_MAC_{F16, F32} %3, %4, %1<tied0>
-    //
-    //  into
-    // %2<tied3> = V_MAC_{F16, F32} %3, %4, %0:sub1<tied0>
-    if (UseOp.isTied() && OpToFold.getSubReg() != AMDGPU::NoSubRegister)
-      return;
   }
 
   // Special case for REG_SEQUENCE: We can't fold literals into

diff --git a/llvm/test/CodeGen/AMDGPU/fold-vgpr-copy.mir b/llvm/test/CodeGen/AMDGPU/fold-vgpr-copy.mir
index 7d1c75c..db57d77 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/fold-vgpr-copy.mir
+++ b/llvm/test/CodeGen/AMDGPU/fold-vgpr-copy.mir
@@ -25,3 +25,19 @@ body:             |
     DS_WRITE2_B32_gfx9 %2, killed %4, killed %3, 0, 1, 0, implicit $exec
 
 ...
+
+# GCN-LABEL: name: fma_sgpr_use
+# GCN: %0:sreg_64_xexec = IMPLICIT_DEF
+# GCN: %4:vgpr_32 = nnan ninf nsz arcp contract afn reassoc V_FMAC_F32_e64 2, %0.sub0, 0, 1073741824, 0, %3, 0, 0, implicit $exec
+
+---
+name:            fma_sgpr_use
+body:             |
+  bb.0:
+    %0:sreg_64_xexec = IMPLICIT_DEF
+    %1:sgpr_32 = COPY %0.sub0
+    %2:sgpr_32 = COPY %0.sub1
+    %3:vgpr_32 = COPY %2
+    %4:vgpr_32 = nnan ninf nsz arcp contract afn reassoc V_FMAC_F32_e64 2, %1, 0, 1073741824, 0, %3, 0, 0, implicit $exec
+    DS_WRITE2_B32_gfx9 undef %5:vgpr_32, killed %4, undef %6:vgpr_32, 0, 1, 0, implicit $exec
+...