[PATCH] D36293: AMDGPU: Look through copies for immediates

[Matt Arsenault via Phabricator via llvm-commits]

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

https://reviews.llvm.org/D36293

Files:
  lib/Target/AMDGPU/SIInstrInfo.cpp
  test/CodeGen/AMDGPU/lshr.v2i16.ll


Index: test/CodeGen/AMDGPU/lshr.v2i16.ll
===================================================================
--- test/CodeGen/AMDGPU/lshr.v2i16.ll
+++ test/CodeGen/AMDGPU/lshr.v2i16.ll
@@ -38,8 +38,7 @@
 ; CI: v_and_b32_e32 v{{[0-9]+}}, [[MASK]], v{{[0-9]+}}
 ; CI: v_bfe_u32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, 16
 ; CI: v_lshrrev_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
-; CI: v_lshlrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
-; CI: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; CI: v_cvt_pk_u16_u32
 define amdgpu_kernel void @v_lshr_v2i16(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %tid.ext = sext i32 %tid to i64
Index: lib/Target/AMDGPU/SIInstrInfo.cpp
===================================================================
--- lib/Target/AMDGPU/SIInstrInfo.cpp
+++ lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -4380,9 +4380,19 @@
 
   if (Op.isReg()) {
     const MachineInstr *Def = MRI.getUniqueVRegDef(Op.getReg());
-    if (!Def || !Def->isMoveImmediate())
+    if (!Def)
       return false;
 
+    if (!Def->isMoveImmediate()) {
+      if (Def->isCopy()) {
+        // Sometimes extra copies are inserted from SGPRs to VGPRs to satisfy
+        // operand constraints.
+        return isImmOrMaterializedImm(MRI, Def->getOperand(1), Imm);
+      }
+
+      return false;
+    }
+
     const MachineOperand &Src = Def->getOperand(1);
     if (Src.isImm()) {
       Imm = Src.getImm();


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D36293.109650.patch
Type: text/x-patch
Size: 1473 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170803/7e15709b/attachment.bin>