[llvm] [AMDGPU] Implemented a patch to optimize SGPR spills (PR #93668)
via llvm-commits
llvm-commits at lists.llvm.org
Wed May 29 04:33:36 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Vikash Gupta (vg0204)
<details>
<summary>Changes</summary>
- As currently, each SGPR Spills are lowered to go into distinct stack slots in stack frame after SGPR allocation phase.
- Therefore, this patch utilizes the capability of StackSlotColoring to ensure the stack slot sharing if possible for stack frame index, where the SGPR spills are occuring in the non-interfering region.
- StackSlotColoring is introduced immediately after SGPR register allocation, just to ensure that any further lowering happens on the optimally allocated stack slots, with certain flags to indicate the preservation of certain analysis result later to be used by RA of other register classes.
---
Patch is 69.26 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/93668.diff
12 Files Affected:
- (modified) llvm/include/llvm/CodeGen/Passes.h (+2)
- (modified) llvm/lib/CodeGen/StackSlotColoring.cpp (+27-2)
- (modified) llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp (+6)
- (modified) llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp (+4-2)
- (modified) llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp (+4-2)
- (modified) llvm/test/CodeGen/AMDGPU/llc-pipeline.ll (+8)
- (modified) llvm/test/CodeGen/AMDGPU/preserve-wwm-copy-dst-reg.ll (+36-36)
- (modified) llvm/test/CodeGen/AMDGPU/sgpr-regalloc-flags.ll (+8)
- (modified) llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll (+42-42)
- (added) llvm/test/CodeGen/AMDGPU/stack-slot-color-after-sgpr-alloc-equal-size-stack-objects.mir (+127)
- (added) llvm/test/CodeGen/AMDGPU/stack-slot-color-after-sgpr-alloc-unequal-size-stack-objects-2.mir (+122)
- (added) llvm/test/CodeGen/AMDGPU/stack-slot-color-after-sgpr-alloc-unequal-size-stack-objects.mir (+123)
``````````diff
diff --git a/llvm/include/llvm/CodeGen/Passes.h b/llvm/include/llvm/CodeGen/Passes.h
index f850767270a4f..172583bc76fa8 100644
--- a/llvm/include/llvm/CodeGen/Passes.h
+++ b/llvm/include/llvm/CodeGen/Passes.h
@@ -371,6 +371,8 @@ namespace llvm {
/// StackSlotColoring - This pass performs stack slot coloring.
extern char &StackSlotColoringID;
+ FunctionPass *
+ createStackSlotColoring(bool preserveRegAllocNeededAnalysis = false);
/// This pass lays out funclets contiguously.
extern char &FuncletLayoutID;
diff --git a/llvm/lib/CodeGen/StackSlotColoring.cpp b/llvm/lib/CodeGen/StackSlotColoring.cpp
index 9fdc8a338b52a..ab58e3dd369cf 100644
--- a/llvm/lib/CodeGen/StackSlotColoring.cpp
+++ b/llvm/lib/CodeGen/StackSlotColoring.cpp
@@ -13,6 +13,7 @@
#include "llvm/ADT/BitVector.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
+#include "llvm/CodeGen/LiveDebugVariables.h"
#include "llvm/CodeGen/LiveInterval.h"
#include "llvm/CodeGen/LiveIntervalUnion.h"
#include "llvm/CodeGen/LiveIntervals.h"
@@ -64,6 +65,10 @@ namespace {
MachineFrameInfo *MFI = nullptr;
const TargetInstrInfo *TII = nullptr;
const MachineBlockFrequencyInfo *MBFI = nullptr;
+ SlotIndexes *Indexes = nullptr;
+
+ // - preserves Analysis passes in case RA may be called afterwards.
+ bool preserveRegAllocNeededAnalysis = false;
// SSIntervals - Spill slot intervals.
std::vector<LiveInterval*> SSIntervals;
@@ -140,7 +145,9 @@ namespace {
public:
static char ID; // Pass identification
- StackSlotColoring() : MachineFunctionPass(ID) {
+ StackSlotColoring(bool preserveRegAllocNeededAnalysis_ = false)
+ : MachineFunctionPass(ID),
+ preserveRegAllocNeededAnalysis(preserveRegAllocNeededAnalysis_) {
initializeStackSlotColoringPass(*PassRegistry::getPassRegistry());
}
@@ -152,6 +159,16 @@ namespace {
AU.addRequired<MachineBlockFrequencyInfo>();
AU.addPreserved<MachineBlockFrequencyInfo>();
AU.addPreservedID(MachineDominatorsID);
+
+ // As in some Target's pipeline, register allocation (RA) might be
+ // splitted into multiple phases based on register class. So, this pass
+ // may be invoked multiple times requiring it to save these analyses to be
+ // used by RA later.
+ if (preserveRegAllocNeededAnalysis) {
+ AU.addPreserved<LiveIntervals>();
+ AU.addPreserved<LiveDebugVariables>();
+ }
+
MachineFunctionPass::getAnalysisUsage(AU);
}
@@ -496,8 +513,10 @@ bool StackSlotColoring::RemoveDeadStores(MachineBasicBlock* MBB) {
++I;
}
- for (MachineInstr *MI : toErase)
+ for (MachineInstr *MI : toErase) {
MI->eraseFromParent();
+ Indexes->removeMachineInstrFromMaps(*MI);
+ }
return changed;
}
@@ -515,6 +534,7 @@ bool StackSlotColoring::runOnMachineFunction(MachineFunction &MF) {
TII = MF.getSubtarget().getInstrInfo();
LS = &getAnalysis<LiveStacks>();
MBFI = &getAnalysis<MachineBlockFrequencyInfo>();
+ Indexes = &getAnalysis<SlotIndexes>();
bool Changed = false;
@@ -549,3 +569,8 @@ bool StackSlotColoring::runOnMachineFunction(MachineFunction &MF) {
return Changed;
}
+
+FunctionPass *
+llvm::createStackSlotColoring(bool preserveRegAllocNeededAnalysis) {
+ return new StackSlotColoring(preserveRegAllocNeededAnalysis);
+}
\ No newline at end of file
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index dbbfe34a63863..2a4b9c2f87e65 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -1406,6 +1406,12 @@ bool GCNPassConfig::addRegAssignAndRewriteOptimized() {
// since FastRegAlloc does the replacements itself.
addPass(createVirtRegRewriter(false));
+ // As by this point SGPR's RA is done introducing SGPR spills to stack frame
+ // through SGPRAllocPass. So, invoking StackSlotColoring here, may allow these
+ // SGPR spills to re-use stack slots, before these spills is further lowered
+ // down via SILowerSGPRSpills(i.e. equivalent of PEI for SGPRs).
+ addPass(createStackSlotColoring(/*preserveRegAllocNeededAnalysis*/ true));
+
// Equivalent of PEI for SGPRs.
addPass(&SILowerSGPRSpillsID);
addPass(&SIPreAllocateWWMRegsID);
diff --git a/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp b/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp
index b6a0152f6fa83..fa3aa9d7091b7 100644
--- a/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp
+++ b/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp
@@ -278,15 +278,16 @@ void SILowerSGPRSpills::extendWWMVirtRegLiveness(MachineFunction &MF,
for (auto Reg : MFI->getSGPRSpillVGPRs()) {
for (MachineBasicBlock *SaveBlock : SaveBlocks) {
MachineBasicBlock::iterator InsertBefore = SaveBlock->begin();
+
DebugLoc DL = SaveBlock->findDebugLoc(InsertBefore);
auto MIB = BuildMI(*SaveBlock, InsertBefore, DL,
TII->get(AMDGPU::IMPLICIT_DEF), Reg);
MFI->setFlag(Reg, AMDGPU::VirtRegFlag::WWM_REG);
// Set SGPR_SPILL asm printer flag
MIB->setAsmPrinterFlag(AMDGPU::SGPR_SPILL);
- if (LIS) {
+
+ if (LIS)
LIS->InsertMachineInstrInMaps(*MIB);
- }
}
}
@@ -300,6 +301,7 @@ void SILowerSGPRSpills::extendWWMVirtRegLiveness(MachineFunction &MF,
auto MIB = BuildMI(*RestoreBlock, InsertBefore, DL,
TII->get(TargetOpcode::KILL));
MIB.addReg(Reg);
+
if (LIS)
LIS->InsertMachineInstrInMaps(*MIB);
}
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
index 4b5f9bdd82b8d..e5829e8193218 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -1775,8 +1775,10 @@ bool SIRegisterInfo::spillSGPR(MachineBasicBlock::iterator MI, int Index,
if (SpillToVGPR) {
- assert(SB.NumSubRegs == VGPRSpills.size() &&
- "Num of VGPR lanes should be equal to num of SGPRs spilled");
+ assert(SB.NumSubRegs <= VGPRSpills.size() &&
+ "Num of VGPR lanes should be greater or equal to num of SGPRs "
+ "spilled, as Stack Slot Coloring pass assigns different SGPR spills "
+ "into same stack slots");
for (unsigned i = 0, e = SB.NumSubRegs; i < e; ++i) {
Register SubReg =
diff --git a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
index 0ff5dd3680dfa..882eab9ba761f 100644
--- a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
+++ b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
@@ -362,10 +362,12 @@
; GCN-O1-NEXT: Machine Optimization Remark Emitter
; GCN-O1-NEXT: Greedy Register Allocator
; GCN-O1-NEXT: Virtual Register Rewriter
+; GCN-O1-NEXT: Stack Slot Coloring
; GCN-O1-NEXT: SI lower SGPR spill instructions
; GCN-O1-NEXT: Virtual Register Map
; GCN-O1-NEXT: Live Register Matrix
; GCN-O1-NEXT: SI Pre-allocate WWM Registers
+; GCN-O1-NEXT: Live Stack Slot Analysis
; GCN-O1-NEXT: Greedy Register Allocator
; GCN-O1-NEXT: SI Lower WWM Copies
; GCN-O1-NEXT: GCN NSA Reassign
@@ -665,10 +667,12 @@
; GCN-O1-OPTS-NEXT: Machine Optimization Remark Emitter
; GCN-O1-OPTS-NEXT: Greedy Register Allocator
; GCN-O1-OPTS-NEXT: Virtual Register Rewriter
+; GCN-O1-OPTS-NEXT: Stack Slot Coloring
; GCN-O1-OPTS-NEXT: SI lower SGPR spill instructions
; GCN-O1-OPTS-NEXT: Virtual Register Map
; GCN-O1-OPTS-NEXT: Live Register Matrix
; GCN-O1-OPTS-NEXT: SI Pre-allocate WWM Registers
+; GCN-O1-OPTS-NEXT: Live Stack Slot Analysis
; GCN-O1-OPTS-NEXT: Greedy Register Allocator
; GCN-O1-OPTS-NEXT: SI Lower WWM Copies
; GCN-O1-OPTS-NEXT: GCN NSA Reassign
@@ -974,10 +978,12 @@
; GCN-O2-NEXT: Machine Optimization Remark Emitter
; GCN-O2-NEXT: Greedy Register Allocator
; GCN-O2-NEXT: Virtual Register Rewriter
+; GCN-O2-NEXT: Stack Slot Coloring
; GCN-O2-NEXT: SI lower SGPR spill instructions
; GCN-O2-NEXT: Virtual Register Map
; GCN-O2-NEXT: Live Register Matrix
; GCN-O2-NEXT: SI Pre-allocate WWM Registers
+; GCN-O2-NEXT: Live Stack Slot Analysis
; GCN-O2-NEXT: Greedy Register Allocator
; GCN-O2-NEXT: SI Lower WWM Copies
; GCN-O2-NEXT: GCN NSA Reassign
@@ -1295,10 +1301,12 @@
; GCN-O3-NEXT: Machine Optimization Remark Emitter
; GCN-O3-NEXT: Greedy Register Allocator
; GCN-O3-NEXT: Virtual Register Rewriter
+; GCN-O3-NEXT: Stack Slot Coloring
; GCN-O3-NEXT: SI lower SGPR spill instructions
; GCN-O3-NEXT: Virtual Register Map
; GCN-O3-NEXT: Live Register Matrix
; GCN-O3-NEXT: SI Pre-allocate WWM Registers
+; GCN-O3-NEXT: Live Stack Slot Analysis
; GCN-O3-NEXT: Greedy Register Allocator
; GCN-O3-NEXT: SI Lower WWM Copies
; GCN-O3-NEXT: GCN NSA Reassign
diff --git a/llvm/test/CodeGen/AMDGPU/preserve-wwm-copy-dst-reg.ll b/llvm/test/CodeGen/AMDGPU/preserve-wwm-copy-dst-reg.ll
index fbe34a3a3970b..25e9e09748c81 100644
--- a/llvm/test/CodeGen/AMDGPU/preserve-wwm-copy-dst-reg.ll
+++ b/llvm/test/CodeGen/AMDGPU/preserve-wwm-copy-dst-reg.ll
@@ -221,15 +221,15 @@ define void @preserve_wwm_copy_dstreg(ptr %parg0, ptr %parg1, ptr %parg2) #0 {
; GFX906-NEXT: ; def s29
; GFX906-NEXT: ;;#ASMEND
; GFX906-NEXT: buffer_load_dword v31, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
-; GFX906-NEXT: v_writelane_b32 v40, s21, 24
-; GFX906-NEXT: v_writelane_b32 v40, s22, 25
-; GFX906-NEXT: v_writelane_b32 v40, s23, 26
-; GFX906-NEXT: v_writelane_b32 v40, s24, 27
-; GFX906-NEXT: v_writelane_b32 v40, s25, 28
-; GFX906-NEXT: v_writelane_b32 v40, s26, 29
-; GFX906-NEXT: v_writelane_b32 v40, s27, 30
-; GFX906-NEXT: v_writelane_b32 v40, s28, 31
-; GFX906-NEXT: v_writelane_b32 v40, s29, 32
+; GFX906-NEXT: v_writelane_b32 v40, s21, 12
+; GFX906-NEXT: v_writelane_b32 v40, s22, 13
+; GFX906-NEXT: v_writelane_b32 v40, s23, 14
+; GFX906-NEXT: v_writelane_b32 v40, s24, 15
+; GFX906-NEXT: v_writelane_b32 v40, s25, 16
+; GFX906-NEXT: v_writelane_b32 v40, s26, 17
+; GFX906-NEXT: v_writelane_b32 v40, s27, 18
+; GFX906-NEXT: v_writelane_b32 v40, s28, 19
+; GFX906-NEXT: v_writelane_b32 v40, s29, 20
; GFX906-NEXT: v_readlane_b32 s4, v40, 10
; GFX906-NEXT: v_readlane_b32 s6, v40, 0
; GFX906-NEXT: v_readlane_b32 s8, v40, 8
@@ -249,39 +249,39 @@ define void @preserve_wwm_copy_dstreg(ptr %parg0, ptr %parg1, ptr %parg2) #0 {
; GFX906-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GFX906-NEXT: s_or_saveexec_b64 s[34:35], -1
; GFX906-NEXT: s_mov_b64 exec, s[34:35]
-; GFX906-NEXT: v_readlane_b32 s21, v40, 24
+; GFX906-NEXT: v_readlane_b32 s21, v40, 12
; GFX906-NEXT: ;;#ASMSTART
; GFX906-NEXT: ; use s21
; GFX906-NEXT: ;;#ASMEND
-; GFX906-NEXT: v_readlane_b32 s22, v40, 25
+; GFX906-NEXT: v_readlane_b32 s22, v40, 13
; GFX906-NEXT: ;;#ASMSTART
; GFX906-NEXT: ; use s22
; GFX906-NEXT: ;;#ASMEND
-; GFX906-NEXT: v_readlane_b32 s23, v40, 26
+; GFX906-NEXT: v_readlane_b32 s23, v40, 14
; GFX906-NEXT: ;;#ASMSTART
; GFX906-NEXT: ; use s23
; GFX906-NEXT: ;;#ASMEND
-; GFX906-NEXT: v_readlane_b32 s24, v40, 27
+; GFX906-NEXT: v_readlane_b32 s24, v40, 15
; GFX906-NEXT: ;;#ASMSTART
; GFX906-NEXT: ; use s24
; GFX906-NEXT: ;;#ASMEND
-; GFX906-NEXT: v_readlane_b32 s25, v40, 28
+; GFX906-NEXT: v_readlane_b32 s25, v40, 16
; GFX906-NEXT: ;;#ASMSTART
; GFX906-NEXT: ; use s25
; GFX906-NEXT: ;;#ASMEND
-; GFX906-NEXT: v_readlane_b32 s26, v40, 29
+; GFX906-NEXT: v_readlane_b32 s26, v40, 17
; GFX906-NEXT: ;;#ASMSTART
; GFX906-NEXT: ; use s26
; GFX906-NEXT: ;;#ASMEND
-; GFX906-NEXT: v_readlane_b32 s27, v40, 30
+; GFX906-NEXT: v_readlane_b32 s27, v40, 18
; GFX906-NEXT: ;;#ASMSTART
; GFX906-NEXT: ; use s27
; GFX906-NEXT: ;;#ASMEND
-; GFX906-NEXT: v_readlane_b32 s28, v40, 31
+; GFX906-NEXT: v_readlane_b32 s28, v40, 19
; GFX906-NEXT: ;;#ASMSTART
; GFX906-NEXT: ; use s28
; GFX906-NEXT: ;;#ASMEND
-; GFX906-NEXT: v_readlane_b32 s29, v40, 32
+; GFX906-NEXT: v_readlane_b32 s29, v40, 20
; GFX906-NEXT: ;;#ASMSTART
; GFX906-NEXT: ; use s29
; GFX906-NEXT: ;;#ASMEND
@@ -602,15 +602,15 @@ define void @preserve_wwm_copy_dstreg(ptr %parg0, ptr %parg1, ptr %parg2) #0 {
; GFX908-NEXT: ; def s29
; GFX908-NEXT: ;;#ASMEND
; GFX908-NEXT: buffer_load_dword v31, off, s[0:3], s33 offset:8 ; 4-byte Folded Reload
-; GFX908-NEXT: v_writelane_b32 v40, s21, 24
-; GFX908-NEXT: v_writelane_b32 v40, s22, 25
-; GFX908-NEXT: v_writelane_b32 v40, s23, 26
-; GFX908-NEXT: v_writelane_b32 v40, s24, 27
-; GFX908-NEXT: v_writelane_b32 v40, s25, 28
-; GFX908-NEXT: v_writelane_b32 v40, s26, 29
-; GFX908-NEXT: v_writelane_b32 v40, s27, 30
-; GFX908-NEXT: v_writelane_b32 v40, s28, 31
-; GFX908-NEXT: v_writelane_b32 v40, s29, 32
+; GFX908-NEXT: v_writelane_b32 v40, s21, 12
+; GFX908-NEXT: v_writelane_b32 v40, s22, 13
+; GFX908-NEXT: v_writelane_b32 v40, s23, 14
+; GFX908-NEXT: v_writelane_b32 v40, s24, 15
+; GFX908-NEXT: v_writelane_b32 v40, s25, 16
+; GFX908-NEXT: v_writelane_b32 v40, s26, 17
+; GFX908-NEXT: v_writelane_b32 v40, s27, 18
+; GFX908-NEXT: v_writelane_b32 v40, s28, 19
+; GFX908-NEXT: v_writelane_b32 v40, s29, 20
; GFX908-NEXT: v_readlane_b32 s4, v40, 10
; GFX908-NEXT: v_readlane_b32 s6, v40, 0
; GFX908-NEXT: v_readlane_b32 s8, v40, 8
@@ -630,39 +630,39 @@ define void @preserve_wwm_copy_dstreg(ptr %parg0, ptr %parg1, ptr %parg2) #0 {
; GFX908-NEXT: s_swappc_b64 s[30:31], s[16:17]
; GFX908-NEXT: s_or_saveexec_b64 s[34:35], -1
; GFX908-NEXT: s_mov_b64 exec, s[34:35]
-; GFX908-NEXT: v_readlane_b32 s21, v40, 24
+; GFX908-NEXT: v_readlane_b32 s21, v40, 12
; GFX908-NEXT: ;;#ASMSTART
; GFX908-NEXT: ; use s21
; GFX908-NEXT: ;;#ASMEND
-; GFX908-NEXT: v_readlane_b32 s22, v40, 25
+; GFX908-NEXT: v_readlane_b32 s22, v40, 13
; GFX908-NEXT: ;;#ASMSTART
; GFX908-NEXT: ; use s22
; GFX908-NEXT: ;;#ASMEND
-; GFX908-NEXT: v_readlane_b32 s23, v40, 26
+; GFX908-NEXT: v_readlane_b32 s23, v40, 14
; GFX908-NEXT: ;;#ASMSTART
; GFX908-NEXT: ; use s23
; GFX908-NEXT: ;;#ASMEND
-; GFX908-NEXT: v_readlane_b32 s24, v40, 27
+; GFX908-NEXT: v_readlane_b32 s24, v40, 15
; GFX908-NEXT: ;;#ASMSTART
; GFX908-NEXT: ; use s24
; GFX908-NEXT: ;;#ASMEND
-; GFX908-NEXT: v_readlane_b32 s25, v40, 28
+; GFX908-NEXT: v_readlane_b32 s25, v40, 16
; GFX908-NEXT: ;;#ASMSTART
; GFX908-NEXT: ; use s25
; GFX908-NEXT: ;;#ASMEND
-; GFX908-NEXT: v_readlane_b32 s26, v40, 29
+; GFX908-NEXT: v_readlane_b32 s26, v40, 17
; GFX908-NEXT: ;;#ASMSTART
; GFX908-NEXT: ; use s26
; GFX908-NEXT: ;;#ASMEND
-; GFX908-NEXT: v_readlane_b32 s27, v40, 30
+; GFX908-NEXT: v_readlane_b32 s27, v40, 18
; GFX908-NEXT: ;;#ASMSTART
; GFX908-NEXT: ; use s27
; GFX908-NEXT: ;;#ASMEND
-; GFX908-NEXT: v_readlane_b32 s28, v40, 31
+; GFX908-NEXT: v_readlane_b32 s28, v40, 19
; GFX908-NEXT: ;;#ASMSTART
; GFX908-NEXT: ; use s28
; GFX908-NEXT: ;;#ASMEND
-; GFX908-NEXT: v_readlane_b32 s29, v40, 32
+; GFX908-NEXT: v_readlane_b32 s29, v40, 20
; GFX908-NEXT: ;;#ASMSTART
; GFX908-NEXT: ; use s29
; GFX908-NEXT: ;;#ASMEND
diff --git a/llvm/test/CodeGen/AMDGPU/sgpr-regalloc-flags.ll b/llvm/test/CodeGen/AMDGPU/sgpr-regalloc-flags.ll
index 17a19116735e4..04a9f3cb2d332 100644
--- a/llvm/test/CodeGen/AMDGPU/sgpr-regalloc-flags.ll
+++ b/llvm/test/CodeGen/AMDGPU/sgpr-regalloc-flags.ll
@@ -17,10 +17,12 @@
; DEFAULT: Greedy Register Allocator
; DEFAULT-NEXT: Virtual Register Rewriter
+; DEFAULT-NEXT: Stack Slot Coloring
; DEFAULT-NEXT: SI lower SGPR spill instructions
; DEFAULT-NEXT: Virtual Register Map
; DEFAULT-NEXT: Live Register Matrix
; DEFAULT-NEXT: SI Pre-allocate WWM Registers
+; DEFAULT-NEXT: Live Stack Slot Analysis
; DEFAULT-NEXT: Greedy Register Allocator
; DEFAULT-NEXT: SI Lower WWM Copies
; DEFAULT-NEXT: GCN NSA Reassign
@@ -50,10 +52,12 @@
; BASIC-DEFAULT-NEXT: Live Register Matrix
; BASIC-DEFAULT-NEXT: Basic Register Allocator
; BASIC-DEFAULT-NEXT: Virtual Register Rewriter
+; BASIC-DEFAULT-NEXT: Stack Slot Coloring
; BASIC-DEFAULT-NEXT: SI lower SGPR spill instructions
; BASIC-DEFAULT-NEXT: Virtual Register Map
; BASIC-DEFAULT-NEXT: Live Register Matrix
; BASIC-DEFAULT-NEXT: SI Pre-allocate WWM Registers
+; BASIC-DEFAULT-NEXT: Live Stack Slot Analysis
; BASIC-DEFAULT-NEXT: Bundle Machine CFG Edges
; BASIC-DEFAULT-NEXT: Spill Code Placement Analysis
; BASIC-DEFAULT-NEXT: Lazy Machine Block Frequency Analysis
@@ -69,10 +73,12 @@
; DEFAULT-BASIC: Greedy Register Allocator
; DEFAULT-BASIC-NEXT: Virtual Register Rewriter
+; DEFAULT-BASIC-NEXT: Stack Slot Coloring
; DEFAULT-BASIC-NEXT: SI lower SGPR spill instructions
; DEFAULT-BASIC-NEXT: Virtual Register Map
; DEFAULT-BASIC-NEXT: Live Register Matrix
; DEFAULT-BASIC-NEXT: SI Pre-allocate WWM Registers
+; DEFAULT-BASIC-NEXT: Live Stack Slot Analysis
; DEFAULT-BASIC-NEXT: Basic Register Allocator
; DEFAULT-BASIC-NEXT: SI Lower WWM Copies
; DEFAULT-BASIC-NEXT: GCN NSA Reassign
@@ -90,10 +96,12 @@
; BASIC-BASIC-NEXT: Live Register Matrix
; BASIC-BASIC-NEXT: Basic Register Allocator
; BASIC-BASIC-NEXT: Virtual Register Rewriter
+; BASIC-BASIC-NEXT: Stack Slot Coloring
; BASIC-BASIC-NEXT: SI lower SGPR spill instructions
; BASIC-BASIC-NEXT: Virtual Register Map
; BASIC-BASIC-NEXT: Live Register Matrix
; BASIC-BASIC-NEXT: SI Pre-allocate WWM Registers
+; BASIC-BASIC-NEXT: Live Stack Slot Analysis
; BASIC-BASIC-NEXT: Basic Register Allocator
; BASIC-BASIC-NEXT: SI Lower WWM Copies
; BASIC-BASIC-NEXT: GCN NSA Reassign
diff --git a/llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll b/llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll
index bea2e6d4b45a3..e1bd1523d78a4 100644
--- a/llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll
+++ b/llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll
@@ -10098,7 +10098,7 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: s_mov_b64 s[4:5], s[2:3]
; GFX6-NEXT: v_lshlrev_b32_e32 v5, 8, v0
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:240
-; GFX6-NEXT: s_mov_b32 s2, 0x84400
+; GFX6-NEXT: s_mov_b32 s2, 0x86a00
; GFX6-NEXT: s_mov_b64 s[8:9], exec
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
@@ -10108,7 +10108,7 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
; GFX6-NEXT: s_waitcnt expcnt(0)
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:224
-; GFX6-NEXT: s_mov_b32 s2, 0x84000
+; GFX6-NEXT: s_mov_b32 s2, 0x86600
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
; GFX6-NEXT: s_waitcnt vmcnt(0)
@@ -10117,7 +10117,7 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
; GFX6-NEXT: s_waitcnt expcnt(0)
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:208
-; GFX6-NEXT: s_mov_b32 s2, 0x83c00
+; GFX6-NEXT: s_mov_b32 s2, 0x86200
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
; GFX6-NEXT: s_waitcnt vmcnt(0)
@@ -10126,7 +10126,7 @@ define amdgpu_kernel void @test_limited_sgpr(ptr addrspace(1) %out, ptr addrspac
; GFX6-NEXT: buffer_store_dword v3, off, s[40:43], s2 offset:12 ; 4-byte Folded Spill
; GFX6-NEXT: s_waitcnt expcnt(0)
; GFX6-NEXT: buffer_load_dwordx4 v[0:3], v[5:6], s[4:7], 0 addr64 offset:192
-; GFX6-NEXT: s_mov_b32 s2, 0x83800
+; GFX6-NEXT: s_mov_b32 s2, 0x85e00
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[40:43], s2 ; 4-byte Folded Spill
; GFX6-NEXT: s_waitcnt...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/93668
More information about the llvm-commits
mailing list