[llvm] [AMDGPU] Use glue for convergence tokens at call-like operations (PR #86766)
Sameer Sahasrabuddhe via llvm-commits
llvm-commits at lists.llvm.org
Tue Mar 26 21:32:14 PDT 2024
https://github.com/ssahasra created https://github.com/llvm/llvm-project/pull/86766
The earlier implementation on AMDGPU used explicit token operands at SI_CALL and SI_CALL_ISEL. This is now replaced with CONVERGENCECTRL_GLUE operands, with the following effects:
- The treatment of tokens at call-like operations is now consistent with the treatment at intrinsics.
- Support for tail calls using implicit tokens at SI_TCRETURN "just works".
- The extra parameter at call-like instructions is eliminated, thus restoring those instructions and their handling to the original state.
The new glue node is placed after the existing glue node for the outgoing call parameters, which seems to not interfere with selection of the call-like nodes.
>From 993187028ee025a81937735127c80208dd854b8e Mon Sep 17 00:00:00 2001
From: Sameer Sahasrabuddhe <sameer.sahasrabuddhe at amd.com>
Date: Wed, 27 Mar 2024 09:59:12 +0530
Subject: [PATCH] [AMDGPU] Use glue for convergence tokens at call-like
operations
The earlier implementation on AMDGPU used explicit token operands at SI_CALL and
SI_CALL_ISEL. This is now replaced with CONVERGENCECTRL_GLUE operands, with the
following effects:
- The treatment of tokens at call-like operations is now consistent with the
treatment at intrinsics.
- Support for tail calls using implicit tokens at SI_TCRETURN "just works".
- The extra parameter at call-like instructions is eliminated, thus restoring
those instructions and their handling to the original state.
The new glue node is placed after the existing glue node for the outgoing call
parameters, which seems to not interfere with selection of the call-like nodes.
---
.../SelectionDAG/SelectionDAGBuilder.cpp | 2 -
llvm/lib/Target/AMDGPU/SIISelLowering.cpp | 29 ++-----
llvm/lib/Target/AMDGPU/SIInstructions.td | 8 +-
.../test/CodeGen/AMDGPU/convergence-tokens.ll | 12 +--
.../CodeGen/AMDGPU/isel-amdgpu-cs-chain-cc.ll | 18 -----
.../kernel-vgpr-spill-mubuf-with-voffset.ll | 1 -
.../AMDGPU/need-fp-from-vgpr-spills.ll | 18 ++---
.../AMDGPU/no-source-locations-in-prologue.ll | 1 -
.../AMDGPU/sgpr-spills-split-regalloc.ll | 15 ++--
.../CodeGen/AMDGPU/stacksave_stackrestore.ll | 78 +++++++++----------
llvm/test/CodeGen/AMDGPU/vgpr-liverange-ir.ll | 26 +++----
.../CodeGen/AMDGPU/vgpr_constant_to_sgpr.ll | 1 -
.../AMDGPU/whole-wave-register-spill.ll | 1 -
.../test/CodeGen/AMDGPU/wwm-reserved-spill.ll | 2 -
llvm/test/CodeGen/AMDGPU/wwm-reserved.ll | 4 -
15 files changed, 76 insertions(+), 140 deletions(-)
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 5db32472d197f5..64ead375e08b3e 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -8607,8 +8607,6 @@ void SelectionDAGBuilder::LowerCallTo(const CallBase &CB, SDValue Callee,
if (auto Bundle = CB.getOperandBundle(LLVMContext::OB_convergencectrl)) {
auto *Token = Bundle->Inputs[0].get();
ConvControlToken = getValue(Token);
- } else {
- ConvControlToken = DAG.getUNDEF(MVT::Untyped);
}
TargetLowering::CallLoweringInfo CLI(DAG);
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index 0a4370de0613b3..b1b82848d91bde 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -3833,9 +3833,6 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
Ops.push_back(DAG.getTargetConstant(0, DL, MVT::i64));
}
- if (!IsTailCall)
- Ops.push_back(CLI.ConvergenceControlToken);
-
if (IsTailCall) {
// Each tail call may have to adjust the stack by a different amount, so
// this information must travel along with the operation for eventual
@@ -3862,6 +3859,12 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
if (InGlue.getNode())
Ops.push_back(InGlue);
+ if (SDValue Token = CLI.ConvergenceControlToken) {
+ Ops.push_back(SDValue(DAG.getMachineNode(TargetOpcode::CONVERGENCECTRL_GLUE,
+ DL, MVT::Glue, Token),
+ 0));
+ }
+
SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
// If we're doing a tall call, use a TC_RETURN here rather than an
@@ -5226,24 +5229,8 @@ MachineBasicBlock *SITargetLowering::EmitInstrWithCustomInserter(
MachineInstrBuilder MIB;
MIB = BuildMI(*BB, MI, DL, TII->get(AMDGPU::SI_CALL), ReturnAddrReg);
- for (unsigned I = 0, E = MI.getNumOperands(); I != E; ++I) {
- MachineOperand &MO = MI.getOperand(I);
- if (I != 2) {
- MIB.add(MO);
- continue;
- }
- }
-
- MachineOperand &MO = MI.getOperand(2);
- MachineRegisterInfo &MRI = BB->getParent()->getRegInfo();
- // The token operand is always a register, whose definition is IMPLICIT_DEF
- // iff there was no token on the call.
- if (MachineInstr *Def = MRI.getVRegDef(MO.getReg())) {
- if (Def->getOpcode() != TargetOpcode::IMPLICIT_DEF) {
- MO.setImplicit();
- MIB.add(MO);
- }
- }
+ for (const MachineOperand &MO : MI.operands())
+ MIB.add(MO);
MIB.cloneMemRefs(MI);
MI.eraseFromParent();
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index 1c942dcefdacea..04f3a2f5760532 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -618,8 +618,8 @@ def SI_RETURN : SPseudoInstSI <
// This version is only needed so we can fill in the output register
// in the custom inserter.
def SI_CALL_ISEL : SPseudoInstSI <
- (outs), (ins SSrc_b64:$src0, unknown:$callee, unknown:$token),
- [(AMDGPUcall i64:$src0, tglobaladdr:$callee, untyped:$token)]> {
+ (outs), (ins SSrc_b64:$src0, unknown:$callee),
+ [(AMDGPUcall i64:$src0, tglobaladdr:$callee)]> {
let Size = 4;
let isCall = 1;
let SchedRW = [WriteBranch];
@@ -629,8 +629,8 @@ def SI_CALL_ISEL : SPseudoInstSI <
}
def : GCNPat<
- (AMDGPUcall i64:$src0, (i64 0), untyped:$token),
- (SI_CALL_ISEL $src0, (i64 0), untyped:$token)
+ (AMDGPUcall i64:$src0, (i64 0)),
+ (SI_CALL_ISEL $src0, (i64 0))
>;
// Wrapper around s_swappc_b64 with extra $callee parameter to track
diff --git a/llvm/test/CodeGen/AMDGPU/convergence-tokens.ll b/llvm/test/CodeGen/AMDGPU/convergence-tokens.ll
index 6beccce9400e58..1c8725f52f7eb0 100644
--- a/llvm/test/CodeGen/AMDGPU/convergence-tokens.ll
+++ b/llvm/test/CodeGen/AMDGPU/convergence-tokens.ll
@@ -4,7 +4,7 @@
; CHECK-LABEL: name: basic_call
; CHECK: [[TOKEN:%[0-9]+]]{{[^ ]*}} = CONVERGENCECTRL_ENTRY
-; ISEL: {{.*}} SI_CALL_ISEL {{.*}}, @foo, [[TOKEN]], csr_amdgpu, {{.*}}
+; ISEL: {{.*}} SI_CALL_ISEL {{.*}}, @foo, csr_amdgpu, {{.*}}, implicit [[TOKEN]]
; DEADMI: {{.*}} SI_CALL {{.*}}, @foo, csr_amdgpu, {{.*}}, implicit [[TOKEN]]
; GISEL: {{.*}} G_SI_CALL {{.*}}, @foo, csr_amdgpu, {{.*}}, implicit [[TOKEN]]
define i32 @basic_call(i32 %src) #0 {
@@ -92,15 +92,9 @@ define i32 @nested(i32 %src) #0 {
ret i32 %sum
}
-; COM: FIXME: Tokens on tail-call have not been implemented for SelectionDAG
-; COM: yet; the corresponding checks have been commented out.
-;
; CHECK-LABEL: name: tail_call_void_func_void
-; GISEL: [[TOKEN:%[0-9]+]]{{[^ ]*}} = CONVERGENCECTRL_ENTRY
-; COM: CHECK: [[TOKEN:%[0-9]+]]{{[^ ]*}} = CONVERGENCECTRL_ENTRY
-; COM: ISEL: {{.*}} SI_CALL_ISEL {{.*}}, @external_void_func_void, [[TOKEN]], csr_amdgpu, {{.*}}
-; COM: DEADMI: {{.*}} SI_CALL {{.*}}, @external_void_func_void, csr_amdgpu, {{.*}}, implicit [[TOKEN]]
-; GISEL: {{.*}} SI_TCRETURN {{.*}}, @external_void_func_void, 0, csr_amdgpu, implicit [[TOKEN]]
+; CHECK: [[TOKEN:%[0-9]+]]{{[^ ]*}} = CONVERGENCECTRL_ENTRY
+; CHECK: {{.*}} SI_TCRETURN {{.*}}, @external_void_func_void, 0, csr_amdgpu, {{.*}}implicit [[TOKEN]]
define void @tail_call_void_func_void() #0 {
%t1 = call token @llvm.experimental.convergence.entry()
tail call void @external_void_func_void() [ "convergencectrl"(token %t1) ]
diff --git a/llvm/test/CodeGen/AMDGPU/isel-amdgpu-cs-chain-cc.ll b/llvm/test/CodeGen/AMDGPU/isel-amdgpu-cs-chain-cc.ll
index e015095a4884a5..ab160ffc10ed07 100644
--- a/llvm/test/CodeGen/AMDGPU/isel-amdgpu-cs-chain-cc.ll
+++ b/llvm/test/CodeGen/AMDGPU/isel-amdgpu-cs-chain-cc.ll
@@ -92,7 +92,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc(<4 x i32> inreg %a, <4 x i32> %b
; DAGISEL-GFX11-NEXT: $vgpr5 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr6 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr7 = COPY [[COPY]]
- ; DAGISEL-GFX11-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX11-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7
; DAGISEL-GFX11-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX11-NEXT: S_ENDPGM 0
@@ -122,7 +121,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc(<4 x i32> inreg %a, <4 x i32> %b
; DAGISEL-GFX10-NEXT: $vgpr5 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr6 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr7 = COPY [[COPY]]
- ; DAGISEL-GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX10-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7
; DAGISEL-GFX10-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX10-NEXT: S_ENDPGM 0
@@ -234,7 +232,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_ptr(ptr inreg %a, ptr %b, ptr ad
; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
- ; DAGISEL-GFX11-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX11-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
; DAGISEL-GFX11-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX11-NEXT: S_ENDPGM 0
@@ -272,7 +269,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_ptr(ptr inreg %a, ptr %b, ptr ad
; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
- ; DAGISEL-GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX10-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
; DAGISEL-GFX10-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX10-NEXT: S_ENDPGM 0
@@ -404,7 +400,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_struct( {ptr, i32, <4 x i32>} in
; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr12 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr13 = COPY [[COPY]]
- ; DAGISEL-GFX11-NEXT: [[DEF2:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX11-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13
; DAGISEL-GFX11-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX11-NEXT: S_ENDPGM 0
@@ -454,7 +449,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_struct( {ptr, i32, <4 x i32>} in
; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr12 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr13 = COPY [[COPY]]
- ; DAGISEL-GFX10-NEXT: [[DEF2:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX10-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13
; DAGISEL-GFX10-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX10-NEXT: S_ENDPGM 0
@@ -506,7 +500,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_float(float inreg %a, float %b)
; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
; DAGISEL-GFX11-NEXT: $vgpr0 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr1 = COPY [[COPY]]
- ; DAGISEL-GFX11-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX11-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $vgpr0, implicit $vgpr1
; DAGISEL-GFX11-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX11-NEXT: S_ENDPGM 0
@@ -524,7 +517,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_float(float inreg %a, float %b)
; DAGISEL-GFX10-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr0 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr1 = COPY [[COPY]]
- ; DAGISEL-GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX10-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0, implicit $vgpr1
; DAGISEL-GFX10-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX10-NEXT: S_ENDPGM 0
@@ -576,7 +568,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_half(half inreg %a, half %b) {
; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
; DAGISEL-GFX11-NEXT: $vgpr0 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr1 = COPY [[COPY]]
- ; DAGISEL-GFX11-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX11-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $vgpr0, implicit $vgpr1
; DAGISEL-GFX11-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX11-NEXT: S_ENDPGM 0
@@ -594,7 +585,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_half(half inreg %a, half %b) {
; DAGISEL-GFX10-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr0 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr1 = COPY [[COPY]]
- ; DAGISEL-GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX10-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0, implicit $vgpr1
; DAGISEL-GFX10-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX10-NEXT: S_ENDPGM 0
@@ -646,7 +636,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_bfloat(bfloat inreg %a, bfloat %
; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
; DAGISEL-GFX11-NEXT: $vgpr0 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr1 = COPY [[COPY]]
- ; DAGISEL-GFX11-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX11-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $vgpr0, implicit $vgpr1
; DAGISEL-GFX11-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX11-NEXT: S_ENDPGM 0
@@ -664,7 +653,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_bfloat(bfloat inreg %a, bfloat %
; DAGISEL-GFX10-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr0 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr1 = COPY [[COPY]]
- ; DAGISEL-GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX10-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0, implicit $vgpr1
; DAGISEL-GFX10-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX10-NEXT: S_ENDPGM 0
@@ -716,7 +704,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_i16(i16 inreg %a, i16 %b) {
; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
; DAGISEL-GFX11-NEXT: $vgpr0 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr1 = COPY [[COPY]]
- ; DAGISEL-GFX11-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX11-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $vgpr0, implicit $vgpr1
; DAGISEL-GFX11-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX11-NEXT: S_ENDPGM 0
@@ -734,7 +721,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_i16(i16 inreg %a, i16 %b) {
; DAGISEL-GFX10-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr0 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr1 = COPY [[COPY]]
- ; DAGISEL-GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX10-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0, implicit $vgpr1
; DAGISEL-GFX10-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX10-NEXT: S_ENDPGM 0
@@ -870,7 +856,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_v16i16(<16 x i16> inreg %a, <16
; DAGISEL-GFX11-NEXT: $vgpr13 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr14 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr15 = COPY [[COPY]]
- ; DAGISEL-GFX11-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX11-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15
; DAGISEL-GFX11-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX11-NEXT: S_ENDPGM 0
@@ -916,7 +901,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_cc_v16i16(<16 x i16> inreg %a, <16
; DAGISEL-GFX10-NEXT: $vgpr13 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr14 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr15 = COPY [[COPY]]
- ; DAGISEL-GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX10-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15
; DAGISEL-GFX10-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX10-NEXT: S_ENDPGM 0
@@ -2480,7 +2464,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_many_regs(<36 x i32> inreg %a, <128
; DAGISEL-GFX11-NEXT: $vgpr29 = COPY [[COPY134]]
; DAGISEL-GFX11-NEXT: $vgpr30 = COPY [[COPY133]]
; DAGISEL-GFX11-NEXT: $vgpr31 = COPY [[COPY132]]
- ; DAGISEL-GFX11-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX11-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $vgpr31
; DAGISEL-GFX11-NEXT: ADJCALLSTACKDOWN 0, 528, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX11-NEXT: S_ENDPGM 0
@@ -2827,7 +2810,6 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_many_regs(<36 x i32> inreg %a, <128
; DAGISEL-GFX10-NEXT: $vgpr29 = COPY [[COPY134]]
; DAGISEL-GFX10-NEXT: $vgpr30 = COPY [[COPY133]]
; DAGISEL-GFX10-NEXT: $vgpr31 = COPY [[COPY132]]
- ; DAGISEL-GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
; DAGISEL-GFX10-NEXT: $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @use, csr_amdgpu_si_gfx, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $vgpr31
; DAGISEL-GFX10-NEXT: ADJCALLSTACKDOWN 0, 528, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
; DAGISEL-GFX10-NEXT: S_ENDPGM 0
diff --git a/llvm/test/CodeGen/AMDGPU/kernel-vgpr-spill-mubuf-with-voffset.ll b/llvm/test/CodeGen/AMDGPU/kernel-vgpr-spill-mubuf-with-voffset.ll
index 1acbb091182802..fbf2ee1145ae94 100644
--- a/llvm/test/CodeGen/AMDGPU/kernel-vgpr-spill-mubuf-with-voffset.ll
+++ b/llvm/test/CodeGen/AMDGPU/kernel-vgpr-spill-mubuf-with-voffset.ll
@@ -60,7 +60,6 @@ define amdgpu_kernel void @test_kernel(i32 %val) #0 {
; CHECK-NEXT: ; implicit-def: $sgpr15
; CHECK-NEXT: s_mov_b64 s[0:1], s[20:21]
; CHECK-NEXT: s_mov_b64 s[2:3], s[22:23]
-; CHECK-NEXT: ; implicit-def: $sgpr18_sgpr19
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: s_or_saveexec_b64 s[34:35], -1
diff --git a/llvm/test/CodeGen/AMDGPU/need-fp-from-vgpr-spills.ll b/llvm/test/CodeGen/AMDGPU/need-fp-from-vgpr-spills.ll
index cbdc7bb456346f..69971bca2738ad 100644
--- a/llvm/test/CodeGen/AMDGPU/need-fp-from-vgpr-spills.ll
+++ b/llvm/test/CodeGen/AMDGPU/need-fp-from-vgpr-spills.ll
@@ -27,7 +27,7 @@ define internal fastcc void @csr_vgpr_spill_fp_callee() #0 {
; CHECK-LABEL: csr_vgpr_spill_fp_callee:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; CHECK-NEXT: s_mov_b32 s24, s33
+; CHECK-NEXT: s_mov_b32 s18, s33
; CHECK-NEXT: s_mov_b32 s33, s32
; CHECK-NEXT: s_xor_saveexec_b64 s[16:17], -1
; CHECK-NEXT: buffer_store_dword v1, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
@@ -43,7 +43,6 @@ define internal fastcc void @csr_vgpr_spill_fp_callee() #0 {
; CHECK-NEXT: s_mov_b64 s[20:21], s[0:1]
; CHECK-NEXT: s_mov_b64 s[0:1], s[20:21]
; CHECK-NEXT: s_mov_b64 s[2:3], s[22:23]
-; CHECK-NEXT: ; implicit-def: $sgpr18_sgpr19
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: ;;#ASMSTART
; CHECK-NEXT: ; clobber csr v40
@@ -55,7 +54,7 @@ define internal fastcc void @csr_vgpr_spill_fp_callee() #0 {
; CHECK-NEXT: buffer_load_dword v1, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
; CHECK-NEXT: s_mov_b64 exec, s[4:5]
; CHECK-NEXT: s_add_i32 s32, s32, 0xfffffc00
-; CHECK-NEXT: s_mov_b32 s33, s24
+; CHECK-NEXT: s_mov_b32 s33, s18
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
bb:
@@ -88,7 +87,6 @@ define amdgpu_kernel void @kernel_call() {
; CHECK-NEXT: ; implicit-def: $sgpr15
; CHECK-NEXT: s_mov_b64 s[0:1], s[20:21]
; CHECK-NEXT: s_mov_b64 s[2:3], s[22:23]
-; CHECK-NEXT: ; implicit-def: $sgpr18_sgpr19
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: s_endpgm
bb:
@@ -148,7 +146,6 @@ define amdgpu_kernel void @kernel_tailcall() {
; CHECK-NEXT: ; implicit-def: $sgpr15
; CHECK-NEXT: s_mov_b64 s[0:1], s[20:21]
; CHECK-NEXT: s_mov_b64 s[2:3], s[22:23]
-; CHECK-NEXT: ; implicit-def: $sgpr18_sgpr19
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: s_endpgm
bb:
@@ -173,7 +170,7 @@ define hidden i32 @caller_save_vgpr_spill_fp_tail_call() #0 {
; CHECK-LABEL: caller_save_vgpr_spill_fp_tail_call:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; CHECK-NEXT: s_mov_b32 s24, s33
+; CHECK-NEXT: s_mov_b32 s18, s33
; CHECK-NEXT: s_mov_b32 s33, s32
; CHECK-NEXT: s_xor_saveexec_b64 s[16:17], -1
; CHECK-NEXT: buffer_store_dword v1, off, s[0:3], s33 ; 4-byte Folded Spill
@@ -188,7 +185,6 @@ define hidden i32 @caller_save_vgpr_spill_fp_tail_call() #0 {
; CHECK-NEXT: s_mov_b64 s[20:21], s[0:1]
; CHECK-NEXT: s_mov_b64 s[0:1], s[20:21]
; CHECK-NEXT: s_mov_b64 s[2:3], s[22:23]
-; CHECK-NEXT: ; implicit-def: $sgpr18_sgpr19
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_readlane_b32 s31, v1, 1
; CHECK-NEXT: v_readlane_b32 s30, v1, 0
@@ -196,7 +192,7 @@ define hidden i32 @caller_save_vgpr_spill_fp_tail_call() #0 {
; CHECK-NEXT: buffer_load_dword v1, off, s[0:3], s33 ; 4-byte Folded Reload
; CHECK-NEXT: s_mov_b64 exec, s[4:5]
; CHECK-NEXT: s_add_i32 s32, s32, 0xfffffc00
-; CHECK-NEXT: s_mov_b32 s33, s24
+; CHECK-NEXT: s_mov_b32 s33, s18
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
entry:
@@ -208,7 +204,7 @@ define hidden i32 @caller_save_vgpr_spill_fp() #0 {
; CHECK-LABEL: caller_save_vgpr_spill_fp:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; CHECK-NEXT: s_mov_b32 s25, s33
+; CHECK-NEXT: s_mov_b32 s19, s33
; CHECK-NEXT: s_mov_b32 s33, s32
; CHECK-NEXT: s_xor_saveexec_b64 s[16:17], -1
; CHECK-NEXT: buffer_store_dword v2, off, s[0:3], s33 ; 4-byte Folded Spill
@@ -223,7 +219,6 @@ define hidden i32 @caller_save_vgpr_spill_fp() #0 {
; CHECK-NEXT: s_mov_b64 s[20:21], s[0:1]
; CHECK-NEXT: s_mov_b64 s[0:1], s[20:21]
; CHECK-NEXT: s_mov_b64 s[2:3], s[22:23]
-; CHECK-NEXT: ; implicit-def: $sgpr18_sgpr19
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_readlane_b32 s31, v2, 1
; CHECK-NEXT: v_readlane_b32 s30, v2, 0
@@ -231,7 +226,7 @@ define hidden i32 @caller_save_vgpr_spill_fp() #0 {
; CHECK-NEXT: buffer_load_dword v2, off, s[0:3], s33 ; 4-byte Folded Reload
; CHECK-NEXT: s_mov_b64 exec, s[4:5]
; CHECK-NEXT: s_add_i32 s32, s32, 0xfffffc00
-; CHECK-NEXT: s_mov_b32 s33, s25
+; CHECK-NEXT: s_mov_b32 s33, s19
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
entry:
@@ -263,7 +258,6 @@ define protected amdgpu_kernel void @kernel() {
; CHECK-NEXT: ; implicit-def: $sgpr15
; CHECK-NEXT: s_mov_b64 s[0:1], s[20:21]
; CHECK-NEXT: s_mov_b64 s[2:3], s[22:23]
-; CHECK-NEXT: ; implicit-def: $sgpr18_sgpr19
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: s_endpgm
entry:
diff --git a/llvm/test/CodeGen/AMDGPU/no-source-locations-in-prologue.ll b/llvm/test/CodeGen/AMDGPU/no-source-locations-in-prologue.ll
index 34e67d0993fb7a..9999cb9173b5db 100644
--- a/llvm/test/CodeGen/AMDGPU/no-source-locations-in-prologue.ll
+++ b/llvm/test/CodeGen/AMDGPU/no-source-locations-in-prologue.ll
@@ -32,7 +32,6 @@ define hidden void @_ZL3barv() #0 !dbg !1644 {
; CHECK-NEXT: s_mov_b64 s[20:21], s[0:1]
; CHECK-NEXT: s_mov_b64 s[0:1], s[20:21]
; CHECK-NEXT: s_mov_b64 s[2:3], s[22:23]
-; CHECK-NEXT: ; implicit-def: $sgpr18_sgpr19
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: .Ltmp1:
diff --git a/llvm/test/CodeGen/AMDGPU/sgpr-spills-split-regalloc.ll b/llvm/test/CodeGen/AMDGPU/sgpr-spills-split-regalloc.ll
index 764f4942cbd03c..f523b4a2495f19 100644
--- a/llvm/test/CodeGen/AMDGPU/sgpr-spills-split-regalloc.ll
+++ b/llvm/test/CodeGen/AMDGPU/sgpr-spills-split-regalloc.ll
@@ -16,7 +16,7 @@ define void @spill_sgpr_with_no_lower_vgpr_available() #0 {
; GCN-LABEL: spill_sgpr_with_no_lower_vgpr_available:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN-NEXT: s_mov_b32 s24, s33
+; GCN-NEXT: s_mov_b32 s18, s33
; GCN-NEXT: s_mov_b32 s33, s32
; GCN-NEXT: s_or_saveexec_b64 s[16:17], -1
; GCN-NEXT: buffer_store_dword v255, off, s[0:3], s33 offset:448 ; 4-byte Folded Spill
@@ -150,7 +150,6 @@ define void @spill_sgpr_with_no_lower_vgpr_available() #0 {
; GCN-NEXT: s_mov_b64 s[20:21], s[0:1]
; GCN-NEXT: s_mov_b64 s[0:1], s[20:21]
; GCN-NEXT: s_mov_b64 s[2:3], s[22:23]
-; GCN-NEXT: ; implicit-def: $sgpr18_sgpr19
; GCN-NEXT: s_waitcnt lgkmcnt(0)
; GCN-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GCN-NEXT: v_readlane_b32 s31, v255, 1
@@ -270,7 +269,7 @@ define void @spill_sgpr_with_no_lower_vgpr_available() #0 {
; GCN-NEXT: buffer_load_dword v255, off, s[0:3], s33 offset:448 ; 4-byte Folded Reload
; GCN-NEXT: s_mov_b64 exec, s[4:5]
; GCN-NEXT: s_add_i32 s32, s32, 0xffff8c00
-; GCN-NEXT: s_mov_b32 s33, s24
+; GCN-NEXT: s_mov_b32 s33, s18
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64 s[30:31]
%alloca = alloca i32, align 4, addrspace(5)
@@ -311,7 +310,7 @@ define void @spill_to_lowest_available_vgpr() #0 {
; GCN-LABEL: spill_to_lowest_available_vgpr:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN-NEXT: s_mov_b32 s24, s33
+; GCN-NEXT: s_mov_b32 s18, s33
; GCN-NEXT: s_mov_b32 s33, s32
; GCN-NEXT: s_or_saveexec_b64 s[16:17], -1
; GCN-NEXT: buffer_store_dword v254, off, s[0:3], s33 offset:444 ; 4-byte Folded Spill
@@ -444,7 +443,6 @@ define void @spill_to_lowest_available_vgpr() #0 {
; GCN-NEXT: s_mov_b64 s[20:21], s[0:1]
; GCN-NEXT: s_mov_b64 s[0:1], s[20:21]
; GCN-NEXT: s_mov_b64 s[2:3], s[22:23]
-; GCN-NEXT: ; implicit-def: $sgpr18_sgpr19
; GCN-NEXT: s_waitcnt lgkmcnt(0)
; GCN-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GCN-NEXT: v_readlane_b32 s31, v254, 1
@@ -563,7 +561,7 @@ define void @spill_to_lowest_available_vgpr() #0 {
; GCN-NEXT: buffer_load_dword v254, off, s[0:3], s33 offset:444 ; 4-byte Folded Reload
; GCN-NEXT: s_mov_b64 exec, s[4:5]
; GCN-NEXT: s_add_i32 s32, s32, 0xffff8c00
-; GCN-NEXT: s_mov_b32 s33, s24
+; GCN-NEXT: s_mov_b32 s33, s18
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64 s[30:31]
%alloca = alloca i32, align 4, addrspace(5)
@@ -1530,7 +1528,7 @@ define void @spill_sgpr_no_free_vgpr_ipra() #0 {
; GCN-LABEL: spill_sgpr_no_free_vgpr_ipra:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN-NEXT: s_mov_b32 s24, s33
+; GCN-NEXT: s_mov_b32 s18, s33
; GCN-NEXT: s_mov_b32 s33, s32
; GCN-NEXT: s_add_i32 s32, s32, 0x7400
; GCN-NEXT: buffer_store_dword v40, off, s[0:3], s33 offset:444 ; 4-byte Folded Spill
@@ -1668,7 +1666,6 @@ define void @spill_sgpr_no_free_vgpr_ipra() #0 {
; GCN-NEXT: s_mov_b64 s[20:21], s[0:1]
; GCN-NEXT: s_mov_b64 s[0:1], s[20:21]
; GCN-NEXT: s_mov_b64 s[2:3], s[22:23]
-; GCN-NEXT: ; implicit-def: $sgpr18_sgpr19
; GCN-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GCN-NEXT: s_mov_b64 s[4:5], exec
; GCN-NEXT: s_mov_b64 exec, 1
@@ -1801,7 +1798,7 @@ define void @spill_sgpr_no_free_vgpr_ipra() #0 {
; GCN-NEXT: buffer_load_dword v41, off, s[0:3], s33 offset:440 ; 4-byte Folded Reload
; GCN-NEXT: buffer_load_dword v40, off, s[0:3], s33 offset:444 ; 4-byte Folded Reload
; GCN-NEXT: s_add_i32 s32, s32, 0xffff8c00
-; GCN-NEXT: s_mov_b32 s33, s24
+; GCN-NEXT: s_mov_b32 s33, s18
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64 s[30:31]
call void @child_function_ipra()
diff --git a/llvm/test/CodeGen/AMDGPU/stacksave_stackrestore.ll b/llvm/test/CodeGen/AMDGPU/stacksave_stackrestore.ll
index b8bc01e0b879b5..c6a599094fe431 100644
--- a/llvm/test/CodeGen/AMDGPU/stacksave_stackrestore.ll
+++ b/llvm/test/CodeGen/AMDGPU/stacksave_stackrestore.ll
@@ -916,13 +916,13 @@ define amdgpu_kernel void @kernel_stacksave_stackrestore_call_with_stack_objects
; WAVE32-O0-LABEL: kernel_stacksave_stackrestore_call_with_stack_objects:
; WAVE32-O0: ; %bb.0:
; WAVE32-O0-NEXT: s_mov_b32 s32, 0x1200
-; WAVE32-O0-NEXT: s_getpc_b64 s[24:25]
-; WAVE32-O0-NEXT: s_mov_b32 s24, s0
-; WAVE32-O0-NEXT: s_load_dwordx4 s[24:27], s[24:25], 0x0
+; WAVE32-O0-NEXT: s_getpc_b64 s[20:21]
+; WAVE32-O0-NEXT: s_mov_b32 s20, s0
+; WAVE32-O0-NEXT: s_load_dwordx4 s[20:23], s[20:21], 0x0
; WAVE32-O0-NEXT: s_waitcnt lgkmcnt(0)
-; WAVE32-O0-NEXT: s_bitset0_b32 s27, 21
-; WAVE32-O0-NEXT: s_add_u32 s24, s24, s9
-; WAVE32-O0-NEXT: s_addc_u32 s25, s25, 0
+; WAVE32-O0-NEXT: s_bitset0_b32 s23, 21
+; WAVE32-O0-NEXT: s_add_u32 s20, s20, s9
+; WAVE32-O0-NEXT: s_addc_u32 s21, s21, 0
; WAVE32-O0-NEXT: ; implicit-def: $vgpr3 : SGPR spill to VGPR lane
; WAVE32-O0-NEXT: s_mov_b32 s14, s8
; WAVE32-O0-NEXT: s_mov_b32 s13, s7
@@ -934,17 +934,17 @@ define amdgpu_kernel void @kernel_stacksave_stackrestore_call_with_stack_objects
; WAVE32-O0-NEXT: v_writelane_b32 v3, s0, 0
; WAVE32-O0-NEXT: s_lshr_b32 s0, s0, 5
; WAVE32-O0-NEXT: v_writelane_b32 v3, s0, 1
-; WAVE32-O0-NEXT: s_or_saveexec_b32 s20, -1
-; WAVE32-O0-NEXT: buffer_store_dword v3, off, s[24:27], 0 offset:128 ; 4-byte Folded Spill
-; WAVE32-O0-NEXT: s_mov_b32 exec_lo, s20
+; WAVE32-O0-NEXT: s_or_saveexec_b32 s19, -1
+; WAVE32-O0-NEXT: buffer_store_dword v3, off, s[20:23], 0 offset:128 ; 4-byte Folded Spill
+; WAVE32-O0-NEXT: s_mov_b32 exec_lo, s19
; WAVE32-O0-NEXT: v_mov_b32_e32 v3, 42
-; WAVE32-O0-NEXT: buffer_store_dword v3, off, s[24:27], 0
+; WAVE32-O0-NEXT: buffer_store_dword v3, off, s[20:23], 0
; WAVE32-O0-NEXT: s_waitcnt_vscnt null, 0x0
-; WAVE32-O0-NEXT: s_mov_b64 s[0:1], s[24:25]
-; WAVE32-O0-NEXT: s_mov_b64 s[2:3], s[26:27]
+; WAVE32-O0-NEXT: s_mov_b64 s[0:1], s[20:21]
+; WAVE32-O0-NEXT: s_mov_b64 s[2:3], s[22:23]
; WAVE32-O0-NEXT: s_mov_b32 s6, s32
; WAVE32-O0-NEXT: v_mov_b32_e32 v3, 17
-; WAVE32-O0-NEXT: buffer_store_dword v3, off, s[24:27], s6 offset:4
+; WAVE32-O0-NEXT: buffer_store_dword v3, off, s[20:23], s6 offset:4
; WAVE32-O0-NEXT: s_mov_b32 s6, stack_passed_argument at abs32@hi
; WAVE32-O0-NEXT: s_mov_b32 s16, stack_passed_argument at abs32@lo
; WAVE32-O0-NEXT: ; kill: def $sgpr16 killed $sgpr16 def $sgpr16_sgpr17
@@ -1018,11 +1018,10 @@ define amdgpu_kernel void @kernel_stacksave_stackrestore_call_with_stack_objects
; WAVE32-O0-NEXT: v_mov_b32_e32 v29, s18
; WAVE32-O0-NEXT: ; implicit-def: $sgpr18
; WAVE32-O0-NEXT: v_mov_b32_e32 v30, s18
-; WAVE32-O0-NEXT: ; implicit-def: $sgpr18_sgpr19
; WAVE32-O0-NEXT: s_swappc_b64 s[30:31], s[16:17]
-; WAVE32-O0-NEXT: s_or_saveexec_b32 s20, -1
-; WAVE32-O0-NEXT: buffer_load_dword v0, off, s[24:27], 0 offset:128 ; 4-byte Folded Reload
-; WAVE32-O0-NEXT: s_mov_b32 exec_lo, s20
+; WAVE32-O0-NEXT: s_or_saveexec_b32 s19, -1
+; WAVE32-O0-NEXT: buffer_load_dword v0, off, s[20:23], 0 offset:128 ; 4-byte Folded Reload
+; WAVE32-O0-NEXT: s_mov_b32 exec_lo, s19
; WAVE32-O0-NEXT: s_waitcnt vmcnt(0)
; WAVE32-O0-NEXT: v_readlane_b32 s1, v0, 1
; WAVE32-O0-NEXT: v_readlane_b32 s0, v0, 0
@@ -1137,7 +1136,6 @@ define amdgpu_kernel void @kernel_stacksave_stackrestore_call_with_stack_objects
; WAVE64-O0-NEXT: v_mov_b32_e32 v29, s18
; WAVE64-O0-NEXT: ; implicit-def: $sgpr18
; WAVE64-O0-NEXT: v_mov_b32_e32 v30, s18
-; WAVE64-O0-NEXT: ; implicit-def: $sgpr18_sgpr19
; WAVE64-O0-NEXT: s_swappc_b64 s[30:31], s[16:17]
; WAVE64-O0-NEXT: s_or_saveexec_b64 s[20:21], -1
; WAVE64-O0-NEXT: buffer_load_dword v0, off, s[24:27], 0 offset:128 ; 4-byte Folded Reload
@@ -1155,13 +1153,13 @@ define amdgpu_kernel void @kernel_stacksave_stackrestore_call_with_stack_objects
; WAVE32-WWM-PREALLOC-LABEL: kernel_stacksave_stackrestore_call_with_stack_objects:
; WAVE32-WWM-PREALLOC: ; %bb.0:
; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s32, 0x1200
-; WAVE32-WWM-PREALLOC-NEXT: s_getpc_b64 s[24:25]
-; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s24, s0
-; WAVE32-WWM-PREALLOC-NEXT: s_load_dwordx4 s[24:27], s[24:25], 0x0
+; WAVE32-WWM-PREALLOC-NEXT: s_getpc_b64 s[20:21]
+; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s20, s0
+; WAVE32-WWM-PREALLOC-NEXT: s_load_dwordx4 s[20:23], s[20:21], 0x0
; WAVE32-WWM-PREALLOC-NEXT: s_waitcnt lgkmcnt(0)
-; WAVE32-WWM-PREALLOC-NEXT: s_bitset0_b32 s27, 21
-; WAVE32-WWM-PREALLOC-NEXT: s_add_u32 s24, s24, s9
-; WAVE32-WWM-PREALLOC-NEXT: s_addc_u32 s25, s25, 0
+; WAVE32-WWM-PREALLOC-NEXT: s_bitset0_b32 s23, 21
+; WAVE32-WWM-PREALLOC-NEXT: s_add_u32 s20, s20, s9
+; WAVE32-WWM-PREALLOC-NEXT: s_addc_u32 s21, s21, 0
; WAVE32-WWM-PREALLOC-NEXT: ; implicit-def: $vgpr32 : SGPR spill to VGPR lane
; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s14, s8
; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s13, s7
@@ -1174,13 +1172,13 @@ define amdgpu_kernel void @kernel_stacksave_stackrestore_call_with_stack_objects
; WAVE32-WWM-PREALLOC-NEXT: s_lshr_b32 s0, s0, 5
; WAVE32-WWM-PREALLOC-NEXT: v_writelane_b32 v32, s0, 1
; WAVE32-WWM-PREALLOC-NEXT: v_mov_b32_e32 v3, 42
-; WAVE32-WWM-PREALLOC-NEXT: buffer_store_dword v3, off, s[24:27], 0
+; WAVE32-WWM-PREALLOC-NEXT: buffer_store_dword v3, off, s[20:23], 0
; WAVE32-WWM-PREALLOC-NEXT: s_waitcnt_vscnt null, 0x0
-; WAVE32-WWM-PREALLOC-NEXT: s_mov_b64 s[0:1], s[24:25]
-; WAVE32-WWM-PREALLOC-NEXT: s_mov_b64 s[2:3], s[26:27]
+; WAVE32-WWM-PREALLOC-NEXT: s_mov_b64 s[0:1], s[20:21]
+; WAVE32-WWM-PREALLOC-NEXT: s_mov_b64 s[2:3], s[22:23]
; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s6, s32
; WAVE32-WWM-PREALLOC-NEXT: v_mov_b32_e32 v3, 17
-; WAVE32-WWM-PREALLOC-NEXT: buffer_store_dword v3, off, s[24:27], s6 offset:4
+; WAVE32-WWM-PREALLOC-NEXT: buffer_store_dword v3, off, s[20:23], s6 offset:4
; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s6, stack_passed_argument at abs32@hi
; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s16, stack_passed_argument at abs32@lo
; WAVE32-WWM-PREALLOC-NEXT: ; kill: def $sgpr16 killed $sgpr16 def $sgpr16_sgpr17
@@ -1254,7 +1252,6 @@ define amdgpu_kernel void @kernel_stacksave_stackrestore_call_with_stack_objects
; WAVE32-WWM-PREALLOC-NEXT: v_mov_b32_e32 v29, s18
; WAVE32-WWM-PREALLOC-NEXT: ; implicit-def: $sgpr18
; WAVE32-WWM-PREALLOC-NEXT: v_mov_b32_e32 v30, s18
-; WAVE32-WWM-PREALLOC-NEXT: ; implicit-def: $sgpr18_sgpr19
; WAVE32-WWM-PREALLOC-NEXT: s_swappc_b64 s[30:31], s[16:17]
; WAVE32-WWM-PREALLOC-NEXT: v_readlane_b32 s1, v32, 1
; WAVE32-WWM-PREALLOC-NEXT: v_readlane_b32 s0, v32, 0
@@ -1347,7 +1344,7 @@ define void @func_stacksave_stackrestore_call_with_stack_objects() {
; WAVE32-O0-LABEL: func_stacksave_stackrestore_call_with_stack_objects:
; WAVE32-O0: ; %bb.0:
; WAVE32-O0-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; WAVE32-O0-NEXT: s_mov_b32 s26, s33
+; WAVE32-O0-NEXT: s_mov_b32 s25, s33
; WAVE32-O0-NEXT: s_mov_b32 s33, s32
; WAVE32-O0-NEXT: s_xor_saveexec_b32 s16, -1
; WAVE32-O0-NEXT: buffer_store_dword v32, off, s[0:3], s33 offset:128 ; 4-byte Folded Spill
@@ -1361,9 +1358,9 @@ define void @func_stacksave_stackrestore_call_with_stack_objects() {
; WAVE32-O0-NEXT: v_writelane_b32 v0, s16, 0
; WAVE32-O0-NEXT: s_lshr_b32 s16, s16, 5
; WAVE32-O0-NEXT: v_writelane_b32 v0, s16, 1
-; WAVE32-O0-NEXT: s_or_saveexec_b32 s25, -1
+; WAVE32-O0-NEXT: s_or_saveexec_b32 s24, -1
; WAVE32-O0-NEXT: buffer_store_dword v0, off, s[0:3], s33 offset:132 ; 4-byte Folded Spill
-; WAVE32-O0-NEXT: s_mov_b32 exec_lo, s25
+; WAVE32-O0-NEXT: s_mov_b32 exec_lo, s24
; WAVE32-O0-NEXT: v_mov_b32_e32 v0, 42
; WAVE32-O0-NEXT: buffer_store_dword v0, off, s[0:3], s33
; WAVE32-O0-NEXT: s_waitcnt_vscnt null, 0x0
@@ -1440,11 +1437,10 @@ define void @func_stacksave_stackrestore_call_with_stack_objects() {
; WAVE32-O0-NEXT: v_mov_b32_e32 v29, s18
; WAVE32-O0-NEXT: ; implicit-def: $sgpr18
; WAVE32-O0-NEXT: v_mov_b32_e32 v30, s18
-; WAVE32-O0-NEXT: ; implicit-def: $sgpr18_sgpr19
; WAVE32-O0-NEXT: s_swappc_b64 s[30:31], s[16:17]
-; WAVE32-O0-NEXT: s_or_saveexec_b32 s25, -1
+; WAVE32-O0-NEXT: s_or_saveexec_b32 s24, -1
; WAVE32-O0-NEXT: buffer_load_dword v0, off, s[0:3], s33 offset:132 ; 4-byte Folded Reload
-; WAVE32-O0-NEXT: s_mov_b32 exec_lo, s25
+; WAVE32-O0-NEXT: s_mov_b32 exec_lo, s24
; WAVE32-O0-NEXT: s_waitcnt vmcnt(0)
; WAVE32-O0-NEXT: v_readlane_b32 s5, v0, 1
; WAVE32-O0-NEXT: v_readlane_b32 s4, v0, 0
@@ -1460,14 +1456,14 @@ define void @func_stacksave_stackrestore_call_with_stack_objects() {
; WAVE32-O0-NEXT: buffer_load_dword v0, off, s[0:3], s33 offset:136 ; 4-byte Folded Reload
; WAVE32-O0-NEXT: s_mov_b32 exec_lo, s4
; WAVE32-O0-NEXT: s_add_i32 s32, s32, 0xffffee00
-; WAVE32-O0-NEXT: s_mov_b32 s33, s26
+; WAVE32-O0-NEXT: s_mov_b32 s33, s25
; WAVE32-O0-NEXT: s_waitcnt vmcnt(0)
; WAVE32-O0-NEXT: s_setpc_b64 s[30:31]
;
; WAVE64-O0-LABEL: func_stacksave_stackrestore_call_with_stack_objects:
; WAVE64-O0: ; %bb.0:
; WAVE64-O0-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; WAVE64-O0-NEXT: s_mov_b32 s28, s33
+; WAVE64-O0-NEXT: s_mov_b32 s19, s33
; WAVE64-O0-NEXT: s_mov_b32 s33, s32
; WAVE64-O0-NEXT: s_xor_saveexec_b64 s[16:17], -1
; WAVE64-O0-NEXT: buffer_store_dword v32, off, s[0:3], s33 offset:128 ; 4-byte Folded Spill
@@ -1560,7 +1556,6 @@ define void @func_stacksave_stackrestore_call_with_stack_objects() {
; WAVE64-O0-NEXT: v_mov_b32_e32 v29, s18
; WAVE64-O0-NEXT: ; implicit-def: $sgpr18
; WAVE64-O0-NEXT: v_mov_b32_e32 v30, s18
-; WAVE64-O0-NEXT: ; implicit-def: $sgpr18_sgpr19
; WAVE64-O0-NEXT: s_swappc_b64 s[30:31], s[16:17]
; WAVE64-O0-NEXT: s_or_saveexec_b64 s[26:27], -1
; WAVE64-O0-NEXT: buffer_load_dword v0, off, s[0:3], s33 offset:132 ; 4-byte Folded Reload
@@ -1580,14 +1575,14 @@ define void @func_stacksave_stackrestore_call_with_stack_objects() {
; WAVE64-O0-NEXT: buffer_load_dword v0, off, s[0:3], s33 offset:136 ; 4-byte Folded Reload
; WAVE64-O0-NEXT: s_mov_b64 exec, s[4:5]
; WAVE64-O0-NEXT: s_add_i32 s32, s32, 0xffffdc00
-; WAVE64-O0-NEXT: s_mov_b32 s33, s28
+; WAVE64-O0-NEXT: s_mov_b32 s33, s19
; WAVE64-O0-NEXT: s_waitcnt vmcnt(0)
; WAVE64-O0-NEXT: s_setpc_b64 s[30:31]
;
; WAVE32-WWM-PREALLOC-LABEL: func_stacksave_stackrestore_call_with_stack_objects:
; WAVE32-WWM-PREALLOC: ; %bb.0:
; WAVE32-WWM-PREALLOC-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s25, s33
+; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s24, s33
; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s33, s32
; WAVE32-WWM-PREALLOC-NEXT: s_xor_saveexec_b32 s16, -1
; WAVE32-WWM-PREALLOC-NEXT: buffer_store_dword v33, off, s[0:3], s33 offset:128 ; 4-byte Folded Spill
@@ -1677,7 +1672,6 @@ define void @func_stacksave_stackrestore_call_with_stack_objects() {
; WAVE32-WWM-PREALLOC-NEXT: v_mov_b32_e32 v29, s18
; WAVE32-WWM-PREALLOC-NEXT: ; implicit-def: $sgpr18
; WAVE32-WWM-PREALLOC-NEXT: v_mov_b32_e32 v30, s18
-; WAVE32-WWM-PREALLOC-NEXT: ; implicit-def: $sgpr18_sgpr19
; WAVE32-WWM-PREALLOC-NEXT: s_swappc_b64 s[30:31], s[16:17]
; WAVE32-WWM-PREALLOC-NEXT: v_readlane_b32 s5, v32, 1
; WAVE32-WWM-PREALLOC-NEXT: v_readlane_b32 s4, v32, 0
@@ -1693,7 +1687,7 @@ define void @func_stacksave_stackrestore_call_with_stack_objects() {
; WAVE32-WWM-PREALLOC-NEXT: buffer_load_dword v32, off, s[0:3], s33 offset:132 ; 4-byte Folded Reload
; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 exec_lo, s4
; WAVE32-WWM-PREALLOC-NEXT: s_add_i32 s32, s32, 0xffffee00
-; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s33, s25
+; WAVE32-WWM-PREALLOC-NEXT: s_mov_b32 s33, s24
; WAVE32-WWM-PREALLOC-NEXT: s_waitcnt vmcnt(0)
; WAVE32-WWM-PREALLOC-NEXT: s_setpc_b64 s[30:31]
%alloca = alloca [32 x i32], addrspace(5)
diff --git a/llvm/test/CodeGen/AMDGPU/vgpr-liverange-ir.ll b/llvm/test/CodeGen/AMDGPU/vgpr-liverange-ir.ll
index d2364a61ed6862..bfc249e9081d22 100644
--- a/llvm/test/CodeGen/AMDGPU/vgpr-liverange-ir.ll
+++ b/llvm/test/CodeGen/AMDGPU/vgpr-liverange-ir.ll
@@ -233,10 +233,10 @@ define amdgpu_ps float @loop(i32 %z, float %v, i32 inreg %bound, ptr %extern_fun
; SI-NEXT: bb.1.Flow:
; SI-NEXT: successors: %bb.2(0x40000000), %bb.10(0x40000000)
; SI-NEXT: {{ $}}
- ; SI-NEXT: [[PHI:%[0-9]+]]:vgpr_32 = PHI undef %49:vgpr_32, %bb.0, %4, %bb.9
- ; SI-NEXT: [[PHI1:%[0-9]+]]:vgpr_32 = PHI [[COPY4]], %bb.0, undef %51:vgpr_32, %bb.9
- ; SI-NEXT: [[PHI2:%[0-9]+]]:vgpr_32 = PHI [[COPY3]], %bb.0, undef %53:vgpr_32, %bb.9
- ; SI-NEXT: [[PHI3:%[0-9]+]]:vgpr_32 = PHI [[COPY2]], %bb.0, undef %55:vgpr_32, %bb.9
+ ; SI-NEXT: [[PHI:%[0-9]+]]:vgpr_32 = PHI undef %47:vgpr_32, %bb.0, %4, %bb.9
+ ; SI-NEXT: [[PHI1:%[0-9]+]]:vgpr_32 = PHI [[COPY4]], %bb.0, undef %49:vgpr_32, %bb.9
+ ; SI-NEXT: [[PHI2:%[0-9]+]]:vgpr_32 = PHI [[COPY3]], %bb.0, undef %51:vgpr_32, %bb.9
+ ; SI-NEXT: [[PHI3:%[0-9]+]]:vgpr_32 = PHI [[COPY2]], %bb.0, undef %53:vgpr_32, %bb.9
; SI-NEXT: [[SI_ELSE:%[0-9]+]]:sreg_32 = SI_ELSE killed [[SI_IF]], %bb.10, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
; SI-NEXT: S_BRANCH %bb.2
; SI-NEXT: {{ $}}
@@ -249,8 +249,8 @@ define amdgpu_ps float @loop(i32 %z, float %v, i32 inreg %bound, ptr %extern_fun
; SI-NEXT: bb.3:
; SI-NEXT: successors: %bb.4(0x80000000)
; SI-NEXT: {{ $}}
- ; SI-NEXT: [[PHI4:%[0-9]+]]:vreg_64 = PHI undef %57:vreg_64, %bb.4, [[REG_SEQUENCE]], %bb.2
- ; SI-NEXT: [[PHI5:%[0-9]+]]:vgpr_32 = PHI undef %59:vgpr_32, %bb.4, [[PHI1]], %bb.2
+ ; SI-NEXT: [[PHI4:%[0-9]+]]:vreg_64 = PHI undef %55:vreg_64, %bb.4, [[REG_SEQUENCE]], %bb.2
+ ; SI-NEXT: [[PHI5:%[0-9]+]]:vgpr_32 = PHI undef %57:vgpr_32, %bb.4, [[PHI1]], %bb.2
; SI-NEXT: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sgpr_32 = V_READFIRSTLANE_B32 [[PHI4]].sub0, implicit $exec
; SI-NEXT: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sgpr_32 = V_READFIRSTLANE_B32 [[PHI4]].sub1, implicit $exec
; SI-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:sgpr_64 = REG_SEQUENCE killed [[V_READFIRSTLANE_B32_]], %subreg.sub0, killed [[V_READFIRSTLANE_B32_1]], %subreg.sub1
@@ -286,8 +286,8 @@ define amdgpu_ps float @loop(i32 %z, float %v, i32 inreg %bound, ptr %extern_fun
; SI-NEXT: bb.7:
; SI-NEXT: successors: %bb.8(0x80000000)
; SI-NEXT: {{ $}}
- ; SI-NEXT: [[PHI6:%[0-9]+]]:vreg_64 = PHI undef %61:vreg_64, %bb.8, [[REG_SEQUENCE2]], %bb.6
- ; SI-NEXT: [[PHI7:%[0-9]+]]:vgpr_32 = PHI undef %63:vgpr_32, %bb.8, [[COPY4]], %bb.6
+ ; SI-NEXT: [[PHI6:%[0-9]+]]:vreg_64 = PHI undef %59:vreg_64, %bb.8, [[REG_SEQUENCE2]], %bb.6
+ ; SI-NEXT: [[PHI7:%[0-9]+]]:vgpr_32 = PHI undef %61:vgpr_32, %bb.8, [[COPY4]], %bb.6
; SI-NEXT: [[V_READFIRSTLANE_B32_2:%[0-9]+]]:sgpr_32 = V_READFIRSTLANE_B32 [[PHI6]].sub0, implicit $exec
; SI-NEXT: [[V_READFIRSTLANE_B32_3:%[0-9]+]]:sgpr_32 = V_READFIRSTLANE_B32 [[PHI6]].sub1, implicit $exec
; SI-NEXT: [[REG_SEQUENCE3:%[0-9]+]]:sgpr_64 = REG_SEQUENCE killed [[V_READFIRSTLANE_B32_2]], %subreg.sub0, killed [[V_READFIRSTLANE_B32_3]], %subreg.sub1
@@ -356,9 +356,9 @@ define amdgpu_ps float @loop_with_use(i32 %z, float %v, i32 inreg %bound, ptr %e
; SI-NEXT: bb.1.Flow:
; SI-NEXT: successors: %bb.2(0x40000000), %bb.10(0x40000000)
; SI-NEXT: {{ $}}
- ; SI-NEXT: [[PHI:%[0-9]+]]:vgpr_32 = PHI undef %50:vgpr_32, %bb.0, %4, %bb.9
- ; SI-NEXT: [[PHI1:%[0-9]+]]:vgpr_32 = PHI [[COPY3]], %bb.0, undef %52:vgpr_32, %bb.9
- ; SI-NEXT: [[PHI2:%[0-9]+]]:vgpr_32 = PHI [[COPY2]], %bb.0, undef %54:vgpr_32, %bb.9
+ ; SI-NEXT: [[PHI:%[0-9]+]]:vgpr_32 = PHI undef %48:vgpr_32, %bb.0, %4, %bb.9
+ ; SI-NEXT: [[PHI1:%[0-9]+]]:vgpr_32 = PHI [[COPY3]], %bb.0, undef %50:vgpr_32, %bb.9
+ ; SI-NEXT: [[PHI2:%[0-9]+]]:vgpr_32 = PHI [[COPY2]], %bb.0, undef %52:vgpr_32, %bb.9
; SI-NEXT: [[SI_ELSE:%[0-9]+]]:sreg_32 = SI_ELSE killed [[SI_IF]], %bb.10, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
; SI-NEXT: S_BRANCH %bb.2
; SI-NEXT: {{ $}}
@@ -371,7 +371,7 @@ define amdgpu_ps float @loop_with_use(i32 %z, float %v, i32 inreg %bound, ptr %e
; SI-NEXT: bb.3:
; SI-NEXT: successors: %bb.4(0x80000000)
; SI-NEXT: {{ $}}
- ; SI-NEXT: [[PHI3:%[0-9]+]]:vreg_64 = PHI undef %56:vreg_64, %bb.4, [[REG_SEQUENCE]], %bb.2
+ ; SI-NEXT: [[PHI3:%[0-9]+]]:vreg_64 = PHI undef %54:vreg_64, %bb.4, [[REG_SEQUENCE]], %bb.2
; SI-NEXT: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sgpr_32 = V_READFIRSTLANE_B32 [[PHI3]].sub0, implicit $exec
; SI-NEXT: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sgpr_32 = V_READFIRSTLANE_B32 [[PHI3]].sub1, implicit $exec
; SI-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:sgpr_64 = REG_SEQUENCE killed [[V_READFIRSTLANE_B32_]], %subreg.sub0, killed [[V_READFIRSTLANE_B32_1]], %subreg.sub1
@@ -407,7 +407,7 @@ define amdgpu_ps float @loop_with_use(i32 %z, float %v, i32 inreg %bound, ptr %e
; SI-NEXT: bb.7:
; SI-NEXT: successors: %bb.8(0x80000000)
; SI-NEXT: {{ $}}
- ; SI-NEXT: [[PHI4:%[0-9]+]]:vreg_64 = PHI undef %58:vreg_64, %bb.8, [[REG_SEQUENCE2]], %bb.6
+ ; SI-NEXT: [[PHI4:%[0-9]+]]:vreg_64 = PHI undef %56:vreg_64, %bb.8, [[REG_SEQUENCE2]], %bb.6
; SI-NEXT: [[V_READFIRSTLANE_B32_2:%[0-9]+]]:sgpr_32 = V_READFIRSTLANE_B32 [[PHI4]].sub0, implicit $exec
; SI-NEXT: [[V_READFIRSTLANE_B32_3:%[0-9]+]]:sgpr_32 = V_READFIRSTLANE_B32 [[PHI4]].sub1, implicit $exec
; SI-NEXT: [[REG_SEQUENCE3:%[0-9]+]]:sgpr_64 = REG_SEQUENCE killed [[V_READFIRSTLANE_B32_2]], %subreg.sub0, killed [[V_READFIRSTLANE_B32_3]], %subreg.sub1
diff --git a/llvm/test/CodeGen/AMDGPU/vgpr_constant_to_sgpr.ll b/llvm/test/CodeGen/AMDGPU/vgpr_constant_to_sgpr.ll
index 37f207fc7a5433..4939d52651d96b 100644
--- a/llvm/test/CodeGen/AMDGPU/vgpr_constant_to_sgpr.ll
+++ b/llvm/test/CodeGen/AMDGPU/vgpr_constant_to_sgpr.ll
@@ -47,7 +47,6 @@ define protected amdgpu_kernel void @kern(ptr %addr) !llvm.amdgcn.lds.kernel.id
; CHECK-NEXT: s_mov_b32 s15, 42
; CHECK-NEXT: s_mov_b64 s[0:1], s[20:21]
; CHECK-NEXT: s_mov_b64 s[2:3], s[22:23]
-; CHECK-NEXT: ; implicit-def: $sgpr18_sgpr19
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: s_endpgm
diff --git a/llvm/test/CodeGen/AMDGPU/whole-wave-register-spill.ll b/llvm/test/CodeGen/AMDGPU/whole-wave-register-spill.ll
index 3a33194f17c875..7eabe982ff2bcd 100644
--- a/llvm/test/CodeGen/AMDGPU/whole-wave-register-spill.ll
+++ b/llvm/test/CodeGen/AMDGPU/whole-wave-register-spill.ll
@@ -101,7 +101,6 @@ define void @test() #0 {
; GCN-O0-NEXT: s_mov_b64 s[20:21], s[0:1]
; GCN-O0-NEXT: s_mov_b64 s[0:1], s[20:21]
; GCN-O0-NEXT: s_mov_b64 s[2:3], s[22:23]
-; GCN-O0-NEXT: ; implicit-def: $sgpr18_sgpr19
; GCN-O0-NEXT: s_waitcnt lgkmcnt(0)
; GCN-O0-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GCN-O0-NEXT: s_or_saveexec_b64 s[28:29], -1
diff --git a/llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll b/llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll
index 11f6a2960776b0..e79cb66dcd7760 100644
--- a/llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll
+++ b/llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll
@@ -406,7 +406,6 @@ define amdgpu_gfx void @strict_wwm_call(ptr addrspace(8) inreg %tmp14, i32 inreg
; GFX9-O0-NEXT: s_mov_b64 s[0:1], s[44:45]
; GFX9-O0-NEXT: s_mov_b64 s[2:3], s[46:47]
; GFX9-O0-NEXT: v_mov_b32_e32 v0, v2
-; GFX9-O0-NEXT: ; implicit-def: $sgpr44_sgpr45
; GFX9-O0-NEXT: s_swappc_b64 s[30:31], s[42:43]
; GFX9-O0-NEXT: v_mov_b32_e32 v1, v0
; GFX9-O0-NEXT: v_add_u32_e64 v1, v1, v2
@@ -633,7 +632,6 @@ define amdgpu_gfx void @strict_wwm_call_i64(ptr addrspace(8) inreg %tmp14, i64 i
; GFX9-O0-NEXT: s_mov_b64 s[2:3], s[38:39]
; GFX9-O0-NEXT: v_mov_b32_e32 v0, v2
; GFX9-O0-NEXT: v_mov_b32_e32 v1, v3
-; GFX9-O0-NEXT: ; implicit-def: $sgpr36_sgpr37
; GFX9-O0-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-O0-NEXT: s_swappc_b64 s[30:31], s[34:35]
; GFX9-O0-NEXT: s_or_saveexec_b64 s[46:47], -1
diff --git a/llvm/test/CodeGen/AMDGPU/wwm-reserved.ll b/llvm/test/CodeGen/AMDGPU/wwm-reserved.ll
index e5cebc1c31832c..def51f2b16d3e9 100644
--- a/llvm/test/CodeGen/AMDGPU/wwm-reserved.ll
+++ b/llvm/test/CodeGen/AMDGPU/wwm-reserved.ll
@@ -413,7 +413,6 @@ define amdgpu_kernel void @call(ptr addrspace(8) inreg %tmp14, i32 inreg %arg) {
; GFX9-O0-NEXT: ; implicit-def: $sgpr15
; GFX9-O0-NEXT: v_mov_b32_e32 v31, v3
; GFX9-O0-NEXT: v_mov_b32_e32 v0, v6
-; GFX9-O0-NEXT: ; implicit-def: $sgpr18_sgpr19
; GFX9-O0-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GFX9-O0-NEXT: s_or_saveexec_b64 s[20:21], -1
; GFX9-O0-NEXT: buffer_load_dword v1, off, s[24:27], 0 ; 4-byte Folded Reload
@@ -657,7 +656,6 @@ define amdgpu_kernel void @call_i64(ptr addrspace(8) inreg %tmp14, i64 inreg %ar
; GFX9-O0-NEXT: v_mov_b32_e32 v31, v3
; GFX9-O0-NEXT: v_mov_b32_e32 v0, v6
; GFX9-O0-NEXT: v_mov_b32_e32 v1, v7
-; GFX9-O0-NEXT: ; implicit-def: $sgpr18_sgpr19
; GFX9-O0-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-O0-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GFX9-O0-NEXT: s_or_saveexec_b64 s[20:21], -1
@@ -1285,7 +1283,6 @@ define amdgpu_kernel void @strict_wwm_call(ptr addrspace(8) inreg %tmp14, i32 in
; GFX9-O0-NEXT: ; implicit-def: $sgpr15
; GFX9-O0-NEXT: v_mov_b32_e32 v31, v3
; GFX9-O0-NEXT: v_mov_b32_e32 v0, v6
-; GFX9-O0-NEXT: ; implicit-def: $sgpr18_sgpr19
; GFX9-O0-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GFX9-O0-NEXT: s_or_saveexec_b64 s[20:21], -1
; GFX9-O0-NEXT: buffer_load_dword v1, off, s[24:27], 0 ; 4-byte Folded Reload
@@ -1529,7 +1526,6 @@ define amdgpu_kernel void @strict_wwm_call_i64(ptr addrspace(8) inreg %tmp14, i6
; GFX9-O0-NEXT: v_mov_b32_e32 v31, v3
; GFX9-O0-NEXT: v_mov_b32_e32 v0, v6
; GFX9-O0-NEXT: v_mov_b32_e32 v1, v7
-; GFX9-O0-NEXT: ; implicit-def: $sgpr18_sgpr19
; GFX9-O0-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-O0-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GFX9-O0-NEXT: s_or_saveexec_b64 s[20:21], -1
More information about the llvm-commits
mailing list