[llvm] r306375 - AMDGPU: M0 operands to spill/restore opcodes are dead

[Nicolai Haehnle via llvm-commits]

Author: nha
Date: Tue Jun 27 01:04:13 2017
New Revision: 306375

URL: http://llvm.org/viewvc/llvm-project?rev=306375&view=rev
Log:
AMDGPU: M0 operands to spill/restore opcodes are dead

Summary:
With scalar stores, M0 is clobbered and therefore marked as implicitly
defined. However, it is also dead.

This fixes an assertion when the Greedy Register Allocator decides to
optimize a spill/restore pair away again (via tryHintsRecoloring).

Reviewers: arsenm

Subscribers: qcolombet, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D33319

Added:
    llvm/trunk/test/CodeGen/AMDGPU/spill-to-smem-m0.ll
Modified:
    llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp

Modified: llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp?rev=306375&r1=306374&r2=306375&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp Tue Jun 27 01:04:13 2017
@@ -770,7 +770,7 @@ void SIInstrInfo::storeRegToStackSlot(Ma
 
     if (ST.hasScalarStores()) {
       // m0 is used for offset to scalar stores if used to spill.
-      Spill.addReg(AMDGPU::M0, RegState::ImplicitDefine);
+      Spill.addReg(AMDGPU::M0, RegState::ImplicitDefine | RegState::Dead);
     }
 
     return;
@@ -871,7 +871,7 @@ void SIInstrInfo::loadRegFromStackSlot(M
 
     if (ST.hasScalarStores()) {
       // m0 is used for offset to scalar stores if used to spill.
-      Spill.addReg(AMDGPU::M0, RegState::ImplicitDefine);
+      Spill.addReg(AMDGPU::M0, RegState::ImplicitDefine | RegState::Dead);
     }
 
     return;

Added: llvm/trunk/test/CodeGen/AMDGPU/spill-to-smem-m0.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/spill-to-smem-m0.ll?rev=306375&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/spill-to-smem-m0.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/spill-to-smem-m0.ll Tue Jun 27 01:04:13 2017
@@ -0,0 +1,22 @@
+; RUN: llc -O0 -march=amdgcn -mcpu=fiji -amdgpu-spill-sgpr-to-smem=1 -verify-machineinstrs -stop-before=prologepilog < %s
+
+; Spill to SMEM clobbers M0. Check that the implicit-def dead operand is present
+; in the pseudo instructions.
+
+; CHECK-LABEL: {{^}}spill_sgpr:
+; CHECK: SI_SPILL_S32_SAVE {{.*}}, implicit-def dead %m0
+; CHECK: SI_SPILL_S32_RESTORE {{.*}}, implicit-def dead %m0
+define amdgpu_kernel void @spill_sgpr(i32 addrspace(1)* %out, i32 %in) #0 {
+  %sgpr = call i32  asm sideeffect "; def $0", "=s" () #0
+  %cmp = icmp eq i32 %in, 0
+  br i1 %cmp, label %bb0, label %ret
+
+bb0:
+  call void asm sideeffect "; use $0", "s"(i32 %sgpr) #0
+  br label %ret
+
+ret:
+  ret void
+}
+
+attributes #0 = { nounwind }