[llvm] 7e43483 - [AMDGPU] Remove set_gpr_idx instructions in conditional blocks

[Jay Foad via llvm-commits]

Author: Jay Foad
Date: 2021-04-30T22:15:45+01:00
New Revision: 7e43483dd1699c34c5bccb56fb6c437e1682d8ad

URL: https://github.com/llvm/llvm-project/commit/7e43483dd1699c34c5bccb56fb6c437e1682d8ad
DIFF: https://github.com/llvm/llvm-project/commit/7e43483dd1699c34c5bccb56fb6c437e1682d8ad.diff

LOG: [AMDGPU] Remove set_gpr_idx instructions in conditional blocks

SIPreEmitPeephole did not try to remove redundant s_set_gpr_idx_*
instructions in blocks that end with a conditional branch instruction.
This seems like a simple oversight.

Differential Revision: https://reviews.llvm.org/D101629

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
    llvm/test/CodeGen/AMDGPU/set-gpr-idx-peephole.mir

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp b/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
index cc06cd8ae717..dce0f4b0df5f 100644
--- a/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
+++ b/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
@@ -349,8 +349,7 @@ bool SIPreEmitPeephole::runOnMachineFunction(MachineFunction &MF) {
   MF.RenumberBlocks();
 
   for (MachineBasicBlock &MBB : MF) {
-    MachineBasicBlock::iterator MBBE = MBB.getFirstTerminator();
-    MachineBasicBlock::iterator TermI = MBBE;
+    MachineBasicBlock::iterator TermI = MBB.getFirstTerminator();
     // Check first terminator for branches to optimize
     if (TermI != MBB.end()) {
       MachineInstr &MI = *TermI;
@@ -358,11 +357,9 @@ bool SIPreEmitPeephole::runOnMachineFunction(MachineFunction &MF) {
       case AMDGPU::S_CBRANCH_VCCZ:
       case AMDGPU::S_CBRANCH_VCCNZ:
         Changed |= optimizeVccBranch(MI);
-        continue;
+        break;
       case AMDGPU::S_CBRANCH_EXECZ:
         Changed |= removeExeczBranch(MI, MBB);
-        continue;
-      default:
         break;
       }
     }
@@ -378,11 +375,8 @@ bool SIPreEmitPeephole::runOnMachineFunction(MachineFunction &MF) {
     // and limit the distance to 20 instructions for compile time purposes.
     // Note: this needs to work on bundles as S_SET_GPR_IDX* instructions
     // may be bundled with the instructions they modify.
-    for (MachineBasicBlock::instr_iterator MBBI = MBB.instr_begin();
-         MBBI != MBBE;) {
-      MachineInstr &MI = *MBBI;
-      ++MBBI;
-
+    for (auto &MI :
+         make_early_inc_range(make_range(MBB.instr_begin(), MBB.instr_end()))) {
       if (Count == Threshold)
         SetGPRMI = nullptr;
       else

diff  --git a/llvm/test/CodeGen/AMDGPU/set-gpr-idx-peephole.mir b/llvm/test/CodeGen/AMDGPU/set-gpr-idx-peephole.mir
index 12490f50f018..27a3f98dd128 100644
--- a/llvm/test/CodeGen/AMDGPU/set-gpr-idx-peephole.mir
+++ b/llvm/test/CodeGen/AMDGPU/set-gpr-idx-peephole.mir
@@ -475,7 +475,6 @@ body:             |
   }
 ...
 
-# FIXME: remove S_SET_GPR_IDX_* despite the branch at the end of the block
 ---
 name:            simple_cbranch_vccz
 body:             |
@@ -484,8 +483,6 @@ body:             |
   ; GCN:   successors: %bb.1(0x80000000)
   ; GCN:   S_SET_GPR_IDX_ON $sgpr2, 1, implicit-def $mode, implicit-def $m0, implicit $mode, implicit undef $m0
   ; GCN:   $vgpr16 = V_MOV_B32_e32 undef $vgpr1, implicit $exec, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $m0
-  ; GCN:   S_SET_GPR_IDX_OFF implicit-def $mode, implicit $mode
-  ; GCN:   S_SET_GPR_IDX_ON killed $sgpr2, 1, implicit-def $mode, implicit-def $m0, implicit $mode, implicit undef $m0
   ; GCN:   $vgpr15 = V_MOV_B32_e32 undef $vgpr0, implicit $exec, implicit killed $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $m0
   ; GCN:   S_SET_GPR_IDX_OFF implicit-def $mode, implicit $mode
   ; GCN:   S_CBRANCH_VCCZ %bb.1, implicit $vcc
@@ -501,7 +498,6 @@ body:             |
   bb.1:
 ...
 
-# FIXME: remove S_SET_GPR_IDX_* despite the branch at the end of the block
 ---
 name:            simple_cbranch_execz
 body:             |
@@ -510,8 +506,6 @@ body:             |
   ; GCN:   successors:
   ; GCN:   S_SET_GPR_IDX_ON $sgpr2, 1, implicit-def $mode, implicit-def $m0, implicit $mode, implicit undef $m0
   ; GCN:   $vgpr16 = V_MOV_B32_e32 undef $vgpr1, implicit $exec, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $m0
-  ; GCN:   S_SET_GPR_IDX_OFF implicit-def $mode, implicit $mode
-  ; GCN:   S_SET_GPR_IDX_ON killed $sgpr2, 1, implicit-def $mode, implicit-def $m0, implicit $mode, implicit undef $m0
   ; GCN:   $vgpr15 = V_MOV_B32_e32 undef $vgpr0, implicit $exec, implicit killed $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $m0
   ; GCN:   S_SET_GPR_IDX_OFF implicit-def $mode, implicit $mode
   ; GCN: bb.1: