[llvm] AMDGPU: Handle folding frame indexes into s_add_i32 (PR #101694)
Matt Arsenault via llvm-commits
llvm-commits at lists.llvm.org
Mon Aug 5 10:36:04 PDT 2024
https://github.com/arsenm updated https://github.com/llvm/llvm-project/pull/101694
>From 0207ca9bd627f90f19690bd9c8362cf85f5ed599 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Thu, 1 Aug 2024 23:11:45 +0400
Subject: [PATCH] AMDGPU: Handle folding frame indexes into s_add_i32
This does not yet enable producing direct frame index
references in s_add_i32, only the lowering.
---
llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp | 63 ++++
.../eliminate-frame-index-s-add-i32.mir | 356 ++++++++++--------
2 files changed, 256 insertions(+), 163 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
index dd4e0d53202d4..43054329304f0 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -2268,7 +2268,70 @@ bool SIRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator MI,
MI->eraseFromParent();
return true;
}
+ case AMDGPU::S_ADD_I32: {
+ // TODO: Handle s_or_b32, s_and_b32.
+ MachineOperand &OtherOp = MI->getOperand(FIOperandNum == 1 ? 2 : 1);
+ assert(FrameReg || MFI->isBottomOfStack());
+
+ MachineOperand &DstOp = MI->getOperand(0);
+ const DebugLoc &DL = MI->getDebugLoc();
+ Register MaterializedReg = FrameReg;
+
+ // Defend against live scc, which should never happen in practice.
+ bool DeadSCC = MI->getOperand(3).isDead();
+
+ // Do an in-place scale of the wave offset to the lane offset.
+ if (FrameReg && !ST.enableFlatScratch()) {
+ BuildMI(*MBB, *MI, DL, TII->get(AMDGPU::S_LSHR_B32))
+ .addDef(DstOp.getReg(), RegState::Renamable)
+ .addReg(FrameReg)
+ .addImm(ST.getWavefrontSizeLog2())
+ .setOperandDead(3); // Set SCC dead
+ MaterializedReg = DstOp.getReg();
+ }
+
+ // If we can't fold the other operand, do another increment.
+ if (!OtherOp.isImm() && MaterializedReg) {
+ auto AddI32 = BuildMI(*MBB, *MI, DL, TII->get(AMDGPU::S_ADD_I32))
+ .addDef(DstOp.getReg(), RegState::Renamable)
+ .addReg(MaterializedReg)
+ .add(OtherOp);
+ if (DeadSCC)
+ AddI32.setOperandDead(3);
+ MaterializedReg = DstOp.getReg();
+ }
+
+ int64_t NewOffset = FrameInfo.getObjectOffset(Index);
+
+ // For the non-immediate case, we could fall through to the default
+ // handling, but we do an in-place update of the result register here to
+ // avoid scavenging another register.
+ if (OtherOp.isImm())
+ NewOffset += OtherOp.getImm();
+
+ if (NewOffset == 0 && DeadSCC) {
+ MI->eraseFromParent();
+ } else if (!MaterializedReg && OtherOp.isImm()) {
+ // In a kernel, the address should just be an immediate.
+ // SCC should really be dead, but preserve the def just in case it
+ // isn't.
+ if (DeadSCC)
+ MI->removeOperand(3);
+ else
+ MI->getOperand(3).setIsDef(true);
+
+ MI->removeOperand(2);
+ MI->getOperand(1).ChangeToImmediate(NewOffset);
+ MI->setDesc(TII->get(AMDGPU::S_MOV_B32));
+ } else {
+ if (MaterializedReg)
+ OtherOp.ChangeToRegister(MaterializedReg, false);
+ FIOp.ChangeToImmediate(NewOffset);
+ }
+
+ return true;
+ }
default: {
// Other access to frame index
const DebugLoc &DL = MI->getDebugLoc();
diff --git a/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-s-add-i32.mir b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-s-add-i32.mir
index a09b39069e5c9..f4742bb7f3ebc 100644
--- a/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-s-add-i32.mir
+++ b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-s-add-i32.mir
@@ -21,21 +21,21 @@ machineFunctionInfo:
body: |
bb.0:
; MUBUFW64-LABEL: name: s_add_i32__inline_imm__fi_offset0
- ; MUBUFW64: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 12, killed $sgpr4, implicit-def dead $scc
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 12, implicit-def dead $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
;
; MUBUFW32-LABEL: name: s_add_i32__inline_imm__fi_offset0
- ; MUBUFW32: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 12, killed $sgpr4, implicit-def dead $scc
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 12, implicit-def dead $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW64-LABEL: name: s_add_i32__inline_imm__fi_offset0
- ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 12, $sgpr32, implicit-def dead $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 12, implicit-def dead $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW32-LABEL: name: s_add_i32__inline_imm__fi_offset0
- ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 12, $sgpr32, implicit-def dead $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 12, implicit-def dead $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
renamable $sgpr7 = S_ADD_I32 12, %stack.0, implicit-def dead $scc
SI_RETURN implicit $sgpr7
@@ -54,21 +54,21 @@ machineFunctionInfo:
body: |
bb.0:
; MUBUFW64-LABEL: name: s_add_i32__fi_offset0__inline_imm
- ; MUBUFW64: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 12, implicit-def dead $scc
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 12, $sgpr7, implicit-def dead $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
;
; MUBUFW32-LABEL: name: s_add_i32__fi_offset0__inline_imm
- ; MUBUFW32: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 12, implicit-def dead $scc
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 12, $sgpr7, implicit-def dead $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW64-LABEL: name: s_add_i32__fi_offset0__inline_imm
- ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 12, implicit-def dead $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 12, $sgpr32, implicit-def dead $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW32-LABEL: name: s_add_i32__fi_offset0__inline_imm
- ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 12, implicit-def dead $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 12, $sgpr32, implicit-def dead $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
renamable $sgpr7 = S_ADD_I32 %stack.0, 12, implicit-def dead $scc
SI_RETURN implicit $sgpr7
@@ -88,25 +88,21 @@ machineFunctionInfo:
body: |
bb.0:
; MUBUFW64-LABEL: name: s_add_i32__inline_imm___fi_offset_inline_imm
- ; MUBUFW64: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def $scc
- ; MUBUFW64-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 16, implicit-def $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 12, killed $sgpr4, implicit-def $scc
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 28, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
;
; MUBUFW32-LABEL: name: s_add_i32__inline_imm___fi_offset_inline_imm
- ; MUBUFW32: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def $scc
- ; MUBUFW32-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 16, implicit-def $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 12, killed $sgpr4, implicit-def $scc
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 28, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW64-LABEL: name: s_add_i32__inline_imm___fi_offset_inline_imm
- ; FLATSCRW64: $sgpr4 = S_ADD_I32 $sgpr32, 16, implicit-def $scc
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 12, killed $sgpr4, implicit-def $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 28, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW32-LABEL: name: s_add_i32__inline_imm___fi_offset_inline_imm
- ; FLATSCRW32: $sgpr4 = S_ADD_I32 $sgpr32, 16, implicit-def $scc
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 12, killed $sgpr4, implicit-def $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 28, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
renamable $sgpr7 = S_ADD_I32 12, %stack.1, implicit-def $scc
SI_RETURN implicit $sgpr7
@@ -125,21 +121,21 @@ machineFunctionInfo:
body: |
bb.0:
; MUBUFW64-LABEL: name: s_add_i32__literal__fi_offset0
- ; MUBUFW64: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 68, killed $sgpr4, implicit-def dead $scc
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 68, implicit-def dead $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
;
; MUBUFW32-LABEL: name: s_add_i32__literal__fi_offset0
- ; MUBUFW32: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 68, killed $sgpr4, implicit-def dead $scc
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 68, implicit-def dead $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW64-LABEL: name: s_add_i32__literal__fi_offset0
- ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 68, $sgpr32, implicit-def dead $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 68, implicit-def dead $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW32-LABEL: name: s_add_i32__literal__fi_offset0
- ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 68, $sgpr32, implicit-def dead $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 68, implicit-def dead $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
renamable $sgpr7 = S_ADD_I32 68, %stack.0, implicit-def dead $scc
SI_RETURN implicit $sgpr7
@@ -158,21 +154,21 @@ machineFunctionInfo:
body: |
bb.0:
; MUBUFW64-LABEL: name: s_add_i32__fi_offset0__literal
- ; MUBUFW64: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 68, implicit-def $scc
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 68, $sgpr7, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
;
; MUBUFW32-LABEL: name: s_add_i32__fi_offset0__literal
- ; MUBUFW32: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 68, implicit-def $scc
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 68, $sgpr7, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW64-LABEL: name: s_add_i32__fi_offset0__literal
- ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 68, implicit-def $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 68, $sgpr32, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW32-LABEL: name: s_add_i32__fi_offset0__literal
- ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 68, implicit-def $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 68, $sgpr32, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
renamable $sgpr7 = S_ADD_I32 %stack.0, 68, implicit-def $scc
SI_RETURN implicit $sgpr7
@@ -192,25 +188,21 @@ machineFunctionInfo:
body: |
bb.0:
; MUBUFW64-LABEL: name: s_add_i32__literal__fi_offset96
- ; MUBUFW64: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def $scc
- ; MUBUFW64-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 96, implicit-def $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 68, killed $sgpr4, implicit-def $scc
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 164, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; MUBUFW32-LABEL: name: s_add_i32__literal__fi_offset96
- ; MUBUFW32: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def $scc
- ; MUBUFW32-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 96, implicit-def $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 68, killed $sgpr4, implicit-def $scc
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 164, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW64-LABEL: name: s_add_i32__literal__fi_offset96
- ; FLATSCRW64: $sgpr4 = S_ADD_I32 $sgpr32, 96, implicit-def $scc
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 68, killed $sgpr4, implicit-def $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 164, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW32-LABEL: name: s_add_i32__literal__fi_offset96
- ; FLATSCRW32: $sgpr4 = S_ADD_I32 $sgpr32, 96, implicit-def $scc
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 68, killed $sgpr4, implicit-def $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 164, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
renamable $sgpr7 = S_ADD_I32 68, %stack.1, implicit-def $scc
SI_RETURN implicit $sgpr7, implicit $scc
@@ -230,25 +222,21 @@ machineFunctionInfo:
body: |
bb.0:
; MUBUFW64-LABEL: name: s_add_i32____fi_offset96__literal
- ; MUBUFW64: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def $scc
- ; MUBUFW64-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 96, implicit-def $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 68, implicit-def $scc
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 164, $sgpr7, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; MUBUFW32-LABEL: name: s_add_i32____fi_offset96__literal
- ; MUBUFW32: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def $scc
- ; MUBUFW32-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 96, implicit-def $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 68, implicit-def $scc
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 164, $sgpr7, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW64-LABEL: name: s_add_i32____fi_offset96__literal
- ; FLATSCRW64: $sgpr4 = S_ADD_I32 $sgpr32, 96, implicit-def $scc
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 68, implicit-def $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 164, $sgpr32, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW32-LABEL: name: s_add_i32____fi_offset96__literal
- ; FLATSCRW32: $sgpr4 = S_ADD_I32 $sgpr32, 96, implicit-def $scc
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 68, implicit-def $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 164, $sgpr32, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
renamable $sgpr7 = S_ADD_I32 %stack.1, 68, implicit-def $scc
SI_RETURN implicit $sgpr7, implicit $scc
@@ -270,27 +258,27 @@ body: |
; MUBUFW64-LABEL: name: s_add_i32__sgpr__fi_offset0
; MUBUFW64: liveins: $sgpr8
; MUBUFW64-NEXT: {{ $}}
- ; MUBUFW64-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
;
; MUBUFW32-LABEL: name: s_add_i32__sgpr__fi_offset0
; MUBUFW32: liveins: $sgpr8
; MUBUFW32-NEXT: {{ $}}
- ; MUBUFW32-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW64-LABEL: name: s_add_i32__sgpr__fi_offset0
; FLATSCRW64: liveins: $sgpr8
; FLATSCRW64-NEXT: {{ $}}
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, $sgpr32, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW32-LABEL: name: s_add_i32__sgpr__fi_offset0
; FLATSCRW32: liveins: $sgpr8
; FLATSCRW32-NEXT: {{ $}}
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, $sgpr32, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
renamable $sgpr7 = S_ADD_I32 $sgpr8, %stack.0, implicit-def dead $scc
SI_RETURN implicit $sgpr7
@@ -312,15 +300,15 @@ body: |
; MUBUFW64-LABEL: name: s_add_i32__fi_offset0__sgpr
; MUBUFW64: liveins: $sgpr8
; MUBUFW64-NEXT: {{ $}}
- ; MUBUFW64-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, $sgpr8, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
;
; MUBUFW32-LABEL: name: s_add_i32__fi_offset0__sgpr
; MUBUFW32: liveins: $sgpr8
; MUBUFW32-NEXT: {{ $}}
- ; MUBUFW32-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, $sgpr8, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW64-LABEL: name: s_add_i32__fi_offset0__sgpr
@@ -355,31 +343,31 @@ body: |
; MUBUFW64-LABEL: name: s_add_i32__sgpr__fi_literal_offset
; MUBUFW64: liveins: $sgpr8
; MUBUFW64-NEXT: {{ $}}
- ; MUBUFW64-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def $scc
- ; MUBUFW64-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 80, implicit-def $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 80, implicit-def dead $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
;
; MUBUFW32-LABEL: name: s_add_i32__sgpr__fi_literal_offset
; MUBUFW32: liveins: $sgpr8
; MUBUFW32-NEXT: {{ $}}
- ; MUBUFW32-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def $scc
- ; MUBUFW32-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 80, implicit-def $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 80, implicit-def dead $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW64-LABEL: name: s_add_i32__sgpr__fi_literal_offset
; FLATSCRW64: liveins: $sgpr8
; FLATSCRW64-NEXT: {{ $}}
- ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 80, implicit-def $scc
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 80, implicit-def dead $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
;
; FLATSCRW32-LABEL: name: s_add_i32__sgpr__fi_literal_offset
; FLATSCRW32: liveins: $sgpr8
; FLATSCRW32-NEXT: {{ $}}
- ; FLATSCRW32-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 80, implicit-def $scc
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 80, implicit-def dead $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
renamable $sgpr7 = S_ADD_I32 $sgpr8, %stack.1, implicit-def dead $scc
SI_RETURN implicit $sgpr7
@@ -402,71 +390,117 @@ body: |
; MUBUFW64-LABEL: name: s_add_i32__fi_literal_offset__sgpr
; MUBUFW64: liveins: $sgpr8
; MUBUFW64-NEXT: {{ $}}
- ; MUBUFW64-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def $scc
- ; MUBUFW64-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 80, implicit-def $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, $sgpr8, implicit-def $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 80, $sgpr7, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; MUBUFW32-LABEL: name: s_add_i32__fi_literal_offset__sgpr
; MUBUFW32: liveins: $sgpr8
; MUBUFW32-NEXT: {{ $}}
- ; MUBUFW32-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def $scc
- ; MUBUFW32-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 80, implicit-def $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, $sgpr8, implicit-def $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 80, $sgpr7, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW64-LABEL: name: s_add_i32__fi_literal_offset__sgpr
; FLATSCRW64: liveins: $sgpr8
; FLATSCRW64-NEXT: {{ $}}
- ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 80, implicit-def $scc
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, $sgpr8, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 80, $sgpr7, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW32-LABEL: name: s_add_i32__fi_literal_offset__sgpr
; FLATSCRW32: liveins: $sgpr8
; FLATSCRW32-NEXT: {{ $}}
- ; FLATSCRW32-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 80, implicit-def $scc
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, $sgpr8, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 80, $sgpr7, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
renamable $sgpr7 = S_ADD_I32 %stack.1, $sgpr8, implicit-def $scc
SI_RETURN implicit $sgpr7, implicit $scc
...
-# FIXME: Fail verifier
-# ---
-# name: s_add_i32__kernel__literal__fi_offset96__offset_literal
-# tracksRegLiveness: true
-# stack:
-# - { id: 0, size: 96, alignment: 16 }
-# - { id: 1, size: 128, alignment: 4 }
-# machineFunctionInfo:
-# scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
-# frameOffsetReg: '$sgpr33'
-# stackPtrOffsetReg: '$sgpr32'
-# isEntryFunction: true
-# body: |
-# bb.0:
-# renamable $sgpr7 = S_ADD_I32 68, %stack.1, implicit-def dead $scc
-# SI_RETURN implicit $sgpr7
-# ...
-
-# ---
-# name: s_add_i32__kernel__fi_offset96__offset_literal__literal
-# tracksRegLiveness: true
-# stack:
-# - { id: 0, size: 96, alignment: 16 }
-# - { id: 1, size: 128, alignment: 4 }
-# machineFunctionInfo:
-# scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
-# frameOffsetReg: '$sgpr33'
-# stackPtrOffsetReg: '$sgpr32'
-# isEntryFunction: true
-# body: |
-# bb.0:
-# renamable $sgpr7 = S_ADD_I32 %stack.1, 68, implicit-def $scc
-# SI_RETURN implicit $sgpr7, implicit $scc
-
-# ...
+
+---
+name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 96, alignment: 16 }
+ - { id: 1, size: 128, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+ ; MUBUFW64: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_MOV_B32 164
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+ ; MUBUFW32: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_MOV_B32 164
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+ ; FLATSCRW64: renamable $sgpr7 = S_MOV_B32 164
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+ ; FLATSCRW32: renamable $sgpr7 = S_MOV_B32 164
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 68, %stack.1, implicit-def dead $scc
+ SI_RETURN implicit $sgpr7
+...
+
+---
+name: s_add_i32__kernel__fi_offset96__offset_literal__literal
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 96, alignment: 16 }
+ - { id: 1, size: 128, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__kernel__fi_offset96__offset_literal__literal
+ ; MUBUFW64: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_MOV_B32 164, implicit-def $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__kernel__fi_offset96__offset_literal__literal
+ ; MUBUFW32: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_MOV_B32 164, implicit-def $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__kernel__fi_offset96__offset_literal__literal
+ ; FLATSCRW64: renamable $sgpr7 = S_MOV_B32 164, implicit-def $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__kernel__fi_offset96__offset_literal__literal
+ ; FLATSCRW32: renamable $sgpr7 = S_MOV_B32 164, implicit-def $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ renamable $sgpr7 = S_ADD_I32 %stack.1, 68, implicit-def $scc
+ SI_RETURN implicit $sgpr7, implicit $scc
+
+...
---
name: s_add_i32__kernel__sgpr__fi_literal_offset
@@ -620,27 +654,31 @@ body: |
; MUBUFW64-LABEL: name: s_add_i32__sgpr__fi_offset0__live_scc
; MUBUFW64: liveins: $sgpr8
; MUBUFW64-NEXT: {{ $}}
- ; MUBUFW64-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 0, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; MUBUFW32-LABEL: name: s_add_i32__sgpr__fi_offset0__live_scc
; MUBUFW32: liveins: $sgpr8
; MUBUFW32-NEXT: {{ $}}
- ; MUBUFW32-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 0, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW64-LABEL: name: s_add_i32__sgpr__fi_offset0__live_scc
; FLATSCRW64: liveins: $sgpr8
; FLATSCRW64-NEXT: {{ $}}
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, $sgpr32, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 0, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW32-LABEL: name: s_add_i32__sgpr__fi_offset0__live_scc
; FLATSCRW32: liveins: $sgpr8
; FLATSCRW32-NEXT: {{ $}}
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, $sgpr32, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 0, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
renamable $sgpr7 = S_ADD_I32 $sgpr8, %stack.0, implicit-def $scc
SI_RETURN implicit $sgpr7, implicit $scc
@@ -709,31 +747,31 @@ body: |
; MUBUFW64-LABEL: name: s_add_i32__sgpr__fi_literal_offset__live_scc
; MUBUFW64: liveins: $sgpr8
; MUBUFW64-NEXT: {{ $}}
- ; MUBUFW64-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def $scc
- ; MUBUFW64-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 96, implicit-def $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 96, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; MUBUFW32-LABEL: name: s_add_i32__sgpr__fi_literal_offset__live_scc
; MUBUFW32: liveins: $sgpr8
; MUBUFW32-NEXT: {{ $}}
- ; MUBUFW32-NEXT: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def $scc
- ; MUBUFW32-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 96, implicit-def $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 96, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW64-LABEL: name: s_add_i32__sgpr__fi_literal_offset__live_scc
; FLATSCRW64: liveins: $sgpr8
; FLATSCRW64-NEXT: {{ $}}
- ; FLATSCRW64-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 96, implicit-def $scc
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 96, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW32-LABEL: name: s_add_i32__sgpr__fi_literal_offset__live_scc
; FLATSCRW32: liveins: $sgpr8
; FLATSCRW32-NEXT: {{ $}}
- ; FLATSCRW32-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 96, implicit-def $scc
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr8, killed $sgpr4, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 96, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
renamable $sgpr7 = S_ADD_I32 $sgpr8, %stack.1, implicit-def $scc
SI_RETURN implicit $sgpr7, implicit $scc
@@ -754,25 +792,21 @@ machineFunctionInfo:
body: |
bb.0:
; MUBUFW64-LABEL: name: s_add_i32__inlineimm__fi_offset_32__total_offset_inlineimm
- ; MUBUFW64: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def $scc
- ; MUBUFW64-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 32, implicit-def $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 8, killed $sgpr4, implicit-def $scc
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 40, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; MUBUFW32-LABEL: name: s_add_i32__inlineimm__fi_offset_32__total_offset_inlineimm
- ; MUBUFW32: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def $scc
- ; MUBUFW32-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 32, implicit-def $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 8, killed $sgpr4, implicit-def $scc
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 40, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW64-LABEL: name: s_add_i32__inlineimm__fi_offset_32__total_offset_inlineimm
- ; FLATSCRW64: $sgpr4 = S_ADD_I32 $sgpr32, 32, implicit-def $scc
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 8, killed $sgpr4, implicit-def $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 40, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW32-LABEL: name: s_add_i32__inlineimm__fi_offset_32__total_offset_inlineimm
- ; FLATSCRW32: $sgpr4 = S_ADD_I32 $sgpr32, 32, implicit-def $scc
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 8, killed $sgpr4, implicit-def $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 40, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
renamable $sgpr7 = S_ADD_I32 8, %stack.1, implicit-def $scc
SI_RETURN implicit $sgpr7, implicit $scc
@@ -792,25 +826,21 @@ machineFunctionInfo:
body: |
bb.0:
; MUBUFW64-LABEL: name: s_add_i32__fi_offset_32__inlineimm__total_offset_inlineimm
- ; MUBUFW64: $sgpr4 = S_LSHR_B32 $sgpr32, 6, implicit-def $scc
- ; MUBUFW64-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 32, implicit-def $scc
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 8, implicit-def $scc
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 40, $sgpr7, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; MUBUFW32-LABEL: name: s_add_i32__fi_offset_32__inlineimm__total_offset_inlineimm
- ; MUBUFW32: $sgpr4 = S_LSHR_B32 $sgpr32, 5, implicit-def $scc
- ; MUBUFW32-NEXT: $sgpr4 = S_ADD_I32 killed $sgpr4, 32, implicit-def $scc
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 8, implicit-def $scc
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 40, $sgpr7, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW64-LABEL: name: s_add_i32__fi_offset_32__inlineimm__total_offset_inlineimm
- ; FLATSCRW64: $sgpr4 = S_ADD_I32 $sgpr32, 32, implicit-def $scc
- ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 8, implicit-def $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 40, $sgpr32, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW32-LABEL: name: s_add_i32__fi_offset_32__inlineimm__total_offset_inlineimm
- ; FLATSCRW32: $sgpr4 = S_ADD_I32 $sgpr32, 32, implicit-def $scc
- ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 killed $sgpr4, 8, implicit-def $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 40, $sgpr32, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
renamable $sgpr7 = S_ADD_I32 %stack.1, 8, implicit-def $scc
SI_RETURN implicit $sgpr7, implicit $scc
@@ -835,7 +865,7 @@ body: |
; MUBUFW64-NEXT: {{ $}}
; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 8, 32, implicit-def $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_MOV_B32 40, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; MUBUFW32-LABEL: name: s_add_i32__kernel_inlineimm__fi_offset_32__total_offset_inlineimm
@@ -843,15 +873,15 @@ body: |
; MUBUFW32-NEXT: {{ $}}
; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 8, 32, implicit-def $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_MOV_B32 40, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW64-LABEL: name: s_add_i32__kernel_inlineimm__fi_offset_32__total_offset_inlineimm
- ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 8, 32, implicit-def $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_MOV_B32 40, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW32-LABEL: name: s_add_i32__kernel_inlineimm__fi_offset_32__total_offset_inlineimm
- ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 8, 32, implicit-def $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_MOV_B32 40, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
renamable $sgpr7 = S_ADD_I32 8, %stack.1, implicit-def $scc
SI_RETURN implicit $sgpr7, implicit $scc
@@ -876,7 +906,7 @@ body: |
; MUBUFW64-NEXT: {{ $}}
; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
- ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 32, 8, implicit-def $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_MOV_B32 40, implicit-def $scc
; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; MUBUFW32-LABEL: name: s_add_i32__kernel_fi_offset_32__inlineimm__total_offset_inlineimm
@@ -884,15 +914,15 @@ body: |
; MUBUFW32-NEXT: {{ $}}
; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
- ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 32, 8, implicit-def $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_MOV_B32 40, implicit-def $scc
; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW64-LABEL: name: s_add_i32__kernel_fi_offset_32__inlineimm__total_offset_inlineimm
- ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 32, 8, implicit-def $scc
+ ; FLATSCRW64: renamable $sgpr7 = S_MOV_B32 40, implicit-def $scc
; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
;
; FLATSCRW32-LABEL: name: s_add_i32__kernel_fi_offset_32__inlineimm__total_offset_inlineimm
- ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 32, 8, implicit-def $scc
+ ; FLATSCRW32: renamable $sgpr7 = S_MOV_B32 40, implicit-def $scc
; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
renamable $sgpr7 = S_ADD_I32 %stack.1, 8, implicit-def $scc
SI_RETURN implicit $sgpr7, implicit $scc
More information about the llvm-commits
mailing list