Skip to content

[AMDGPU] Skip register uses in AMDGPUResourceUsageAnalysis #133242

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 16 commits into from
Jun 3, 2025
Merged

[AMDGPU] Skip register uses in AMDGPUResourceUsageAnalysis #133242

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
8a56150
[AMDGPU] Ignore inactive VGPRs in .vgpr_count
rovka Mar 17, 2025
5089dad
Skip implicit defs unconditionally
rovka Mar 27, 2025
726506f
Skip register uses in AMDGPUResourceUsageAnalysis
rovka Apr 2, 2025
63bba7e
Merge branch 'main' into vgpr-count
rovka Apr 2, 2025
f42baae
s/no-init-whole-wave/isEntryFunction
rovka Apr 3, 2025
affc837
Fix typo in comment. NFC
rovka Apr 7, 2025
733829b
Unify code paths; include user + sys SGPRS if used
rovka Apr 29, 2025
0824cf2
Merge remote-tracking branch 'remotes/origin/main' into vgpr-count
rovka Apr 30, 2025
563cbd6
Add missing tests. Fix preloaded VGPR issue
rovka May 5, 2025
f27621d
Formatting
rovka May 5, 2025
ca7e723
Cound all preloaded regs
rovka May 6, 2025
e45bbf9
Merge remote-tracking branch 'origin/main' into vgpr-count
rovka May 6, 2025
49fa86f
De Morgan
rovka May 26, 2025
3da979a
Comments
rovka May 26, 2025
0dbc113
Merge remote-tracking branch 'remotes/origin/main' into vgpr-count-rovka
rovka May 26, 2025
35af826
Merge branch 'main' into vgpr-count
rovka Jun 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 5 additions & 6 deletions llvm/docs/AMDGPUUsage.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4263,10 +4263,9 @@ same *vendor-name*.
wavefront for
GFX6-GFX9. A register
is required if it is
used explicitly, or
written to, or
if a higher numbered
register is used
explicitly. This
register is written to. This
includes the special
SGPRs for VCC, Flat
Scratch (GFX7-GFX9)
Expand All @@ -4284,10 +4283,10 @@ same *vendor-name*.
each work-item for
GFX6-GFX9. A register
is required if it is
used explicitly, or
written to, or
if a higher numbered
register is used
explicitly.
register is
written to.
".agpr_count" integer Required Number of accumulator
registers required by
each work-item for
Expand Down
11 changes: 1 addition & 10 deletions llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -989,7 +989,7 @@ void AMDGPUAsmPrinter::getSIProgramInfo(SIProgramInfo &ProgInfo,
// dispatch registers are function args.
unsigned WaveDispatchNumSGPR = 0, WaveDispatchNumVGPR = 0;

if (isShader(F.getCallingConv())) {
if (isShader(F.getCallingConv()) && isEntryFunctionCC(F.getCallingConv())) {
bool IsPixelShader =
F.getCallingConv() == CallingConv::AMDGPU_PS && !STM.isAmdHsaOS();

Expand Down Expand Up @@ -1060,15 +1060,6 @@ void AMDGPUAsmPrinter::getSIProgramInfo(SIProgramInfo &ProgInfo,

ProgInfo.NumVGPR = AMDGPUMCExpr::createTotalNumVGPR(
ProgInfo.NumAccVGPR, ProgInfo.NumArchVGPR, Ctx);
} else if (isKernel(F.getCallingConv()) &&
MFI->getNumKernargPreloadedSGPRs()) {
// Consider cases where the total number of UserSGPRs with trailing
// allocated preload SGPRs, is greater than the number of explicitly
// referenced SGPRs.
const MCExpr *UserPlusExtraSGPRs = MCBinaryExpr::createAdd(
CreateExpr(MFI->getNumUserSGPRs()), ExtraSGPRs, Ctx);
ProgInfo.NumSGPR =
AMDGPUMCExpr::createMax({ProgInfo.NumSGPR, UserPlusExtraSGPRs}, Ctx);
}

// Adjust number of registers used to meet default/requested minimum/maximum
Expand Down
283 changes: 17 additions & 266 deletions llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,274 +137,29 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage(
if (MFI->isStackRealigned())
Info.PrivateSegmentSize += FrameInfo.getMaxAlign().value();

Info.UsesVCC =
MRI.isPhysRegUsed(AMDGPU::VCC_LO) || MRI.isPhysRegUsed(AMDGPU::VCC_HI);

// If there are no calls, MachineRegisterInfo can tell us the used register
// count easily.
// A tail call isn't considered a call for MachineFrameInfo's purposes.
if (!FrameInfo.hasCalls() && !FrameInfo.hasTailCall()) {
Info.NumVGPR = TRI.getNumUsedPhysRegs(MRI, AMDGPU::VGPR_32RegClass);
Info.NumExplicitSGPR = TRI.getNumUsedPhysRegs(MRI, AMDGPU::SGPR_32RegClass);
if (ST.hasMAIInsts())
Info.NumAGPR = TRI.getNumUsedPhysRegs(MRI, AMDGPU::AGPR_32RegClass);
return Info;
Info.UsesVCC = MRI.isPhysRegUsed(AMDGPU::VCC);

Info.NumVGPR = TRI.getNumDefinedPhysRegs(MRI, AMDGPU::VGPR_32RegClass);
Info.NumExplicitSGPR =
TRI.getNumDefinedPhysRegs(MRI, AMDGPU::SGPR_32RegClass);
if (ST.hasMAIInsts())
Info.NumAGPR = TRI.getNumDefinedPhysRegs(MRI, AMDGPU::AGPR_32RegClass);

// Preloaded registers are written by the hardware, not defined in the
// function body, so they need special handling.
if (MFI->isEntryFunction()) {
Info.NumExplicitSGPR =
std::max<int32_t>(Info.NumExplicitSGPR, MFI->getNumPreloadedSGPRs());
Info.NumVGPR = std::max<int32_t>(Info.NumVGPR, MFI->getNumPreloadedVGPRs());
}

int32_t MaxVGPR = -1;
int32_t MaxAGPR = -1;
int32_t MaxSGPR = -1;
if (!FrameInfo.hasCalls() && !FrameInfo.hasTailCall())
return Info;

Info.CalleeSegmentSize = 0;

for (const MachineBasicBlock &MBB : MF) {
for (const MachineInstr &MI : MBB) {
// TODO: Check regmasks? Do they occur anywhere except calls?
for (const MachineOperand &MO : MI.operands()) {
unsigned Width = 0;
bool IsSGPR = false;
bool IsAGPR = false;

if (!MO.isReg())
continue;

Register Reg = MO.getReg();
switch (Reg) {
case AMDGPU::EXEC:
case AMDGPU::EXEC_LO:
case AMDGPU::EXEC_HI:
case AMDGPU::SCC:
case AMDGPU::M0:
case AMDGPU::M0_LO16:
case AMDGPU::M0_HI16:
case AMDGPU::SRC_SHARED_BASE_LO:
case AMDGPU::SRC_SHARED_BASE:
case AMDGPU::SRC_SHARED_LIMIT_LO:
case AMDGPU::SRC_SHARED_LIMIT:
case AMDGPU::SRC_PRIVATE_BASE_LO:
case AMDGPU::SRC_PRIVATE_BASE:
case AMDGPU::SRC_PRIVATE_LIMIT_LO:
case AMDGPU::SRC_PRIVATE_LIMIT:
case AMDGPU::SRC_POPS_EXITING_WAVE_ID:
case AMDGPU::SGPR_NULL:
case AMDGPU::SGPR_NULL64:
case AMDGPU::MODE:
continue;

case AMDGPU::NoRegister:
assert(MI.isDebugInstr() &&
"Instruction uses invalid noreg register");
continue;

case AMDGPU::VCC:
case AMDGPU::VCC_LO:
case AMDGPU::VCC_HI:
case AMDGPU::VCC_LO_LO16:
case AMDGPU::VCC_LO_HI16:
case AMDGPU::VCC_HI_LO16:
case AMDGPU::VCC_HI_HI16:
Info.UsesVCC = true;
continue;

case AMDGPU::FLAT_SCR:
case AMDGPU::FLAT_SCR_LO:
case AMDGPU::FLAT_SCR_HI:
continue;

case AMDGPU::XNACK_MASK:
case AMDGPU::XNACK_MASK_LO:
case AMDGPU::XNACK_MASK_HI:
llvm_unreachable("xnack_mask registers should not be used");

case AMDGPU::LDS_DIRECT:
llvm_unreachable("lds_direct register should not be used");

case AMDGPU::TBA:
case AMDGPU::TBA_LO:
case AMDGPU::TBA_HI:
case AMDGPU::TMA:
case AMDGPU::TMA_LO:
case AMDGPU::TMA_HI:
llvm_unreachable("trap handler registers should not be used");

case AMDGPU::SRC_VCCZ:
llvm_unreachable("src_vccz register should not be used");

case AMDGPU::SRC_EXECZ:
llvm_unreachable("src_execz register should not be used");

case AMDGPU::SRC_SCC:
llvm_unreachable("src_scc register should not be used");

default:
break;
}

if (AMDGPU::SGPR_32RegClass.contains(Reg) ||
AMDGPU::SGPR_LO16RegClass.contains(Reg) ||
AMDGPU::SGPR_HI16RegClass.contains(Reg)) {
IsSGPR = true;
Width = 1;
} else if (AMDGPU::VGPR_32RegClass.contains(Reg) ||
AMDGPU::VGPR_16RegClass.contains(Reg)) {
IsSGPR = false;
Width = 1;
} else if (AMDGPU::AGPR_32RegClass.contains(Reg) ||
AMDGPU::AGPR_LO16RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 1;
} else if (AMDGPU::SGPR_64RegClass.contains(Reg)) {
IsSGPR = true;
Width = 2;
} else if (AMDGPU::VReg_64RegClass.contains(Reg)) {
IsSGPR = false;
Width = 2;
} else if (AMDGPU::AReg_64RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 2;
} else if (AMDGPU::VReg_96RegClass.contains(Reg)) {
IsSGPR = false;
Width = 3;
} else if (AMDGPU::SReg_96RegClass.contains(Reg)) {
IsSGPR = true;
Width = 3;
} else if (AMDGPU::AReg_96RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 3;
} else if (AMDGPU::SGPR_128RegClass.contains(Reg)) {
IsSGPR = true;
Width = 4;
} else if (AMDGPU::VReg_128RegClass.contains(Reg)) {
IsSGPR = false;
Width = 4;
} else if (AMDGPU::AReg_128RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 4;
} else if (AMDGPU::VReg_160RegClass.contains(Reg)) {
IsSGPR = false;
Width = 5;
} else if (AMDGPU::SReg_160RegClass.contains(Reg)) {
IsSGPR = true;
Width = 5;
} else if (AMDGPU::AReg_160RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 5;
} else if (AMDGPU::VReg_192RegClass.contains(Reg)) {
IsSGPR = false;
Width = 6;
} else if (AMDGPU::SReg_192RegClass.contains(Reg)) {
IsSGPR = true;
Width = 6;
} else if (AMDGPU::AReg_192RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 6;
} else if (AMDGPU::VReg_224RegClass.contains(Reg)) {
IsSGPR = false;
Width = 7;
} else if (AMDGPU::SReg_224RegClass.contains(Reg)) {
IsSGPR = true;
Width = 7;
} else if (AMDGPU::AReg_224RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 7;
} else if (AMDGPU::SReg_256RegClass.contains(Reg)) {
IsSGPR = true;
Width = 8;
} else if (AMDGPU::VReg_256RegClass.contains(Reg)) {
IsSGPR = false;
Width = 8;
} else if (AMDGPU::AReg_256RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 8;
} else if (AMDGPU::VReg_288RegClass.contains(Reg)) {
IsSGPR = false;
Width = 9;
} else if (AMDGPU::SReg_288RegClass.contains(Reg)) {
IsSGPR = true;
Width = 9;
} else if (AMDGPU::AReg_288RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 9;
} else if (AMDGPU::VReg_320RegClass.contains(Reg)) {
IsSGPR = false;
Width = 10;
} else if (AMDGPU::SReg_320RegClass.contains(Reg)) {
IsSGPR = true;
Width = 10;
} else if (AMDGPU::AReg_320RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 10;
} else if (AMDGPU::VReg_352RegClass.contains(Reg)) {
IsSGPR = false;
Width = 11;
} else if (AMDGPU::SReg_352RegClass.contains(Reg)) {
IsSGPR = true;
Width = 11;
} else if (AMDGPU::AReg_352RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 11;
} else if (AMDGPU::VReg_384RegClass.contains(Reg)) {
IsSGPR = false;
Width = 12;
} else if (AMDGPU::SReg_384RegClass.contains(Reg)) {
IsSGPR = true;
Width = 12;
} else if (AMDGPU::AReg_384RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 12;
} else if (AMDGPU::SReg_512RegClass.contains(Reg)) {
IsSGPR = true;
Width = 16;
} else if (AMDGPU::VReg_512RegClass.contains(Reg)) {
IsSGPR = false;
Width = 16;
} else if (AMDGPU::AReg_512RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 16;
} else if (AMDGPU::SReg_1024RegClass.contains(Reg)) {
IsSGPR = true;
Width = 32;
} else if (AMDGPU::VReg_1024RegClass.contains(Reg)) {
IsSGPR = false;
Width = 32;
} else if (AMDGPU::AReg_1024RegClass.contains(Reg)) {
IsSGPR = false;
IsAGPR = true;
Width = 32;
} else {
// We only expect TTMP registers or registers that do not belong to
// any RC.
assert((AMDGPU::TTMP_32RegClass.contains(Reg) ||
AMDGPU::TTMP_64RegClass.contains(Reg) ||
AMDGPU::TTMP_128RegClass.contains(Reg) ||
AMDGPU::TTMP_256RegClass.contains(Reg) ||
AMDGPU::TTMP_512RegClass.contains(Reg) ||
!TRI.getPhysRegBaseClass(Reg)) &&
"Unknown register class");
}
unsigned HWReg = TRI.getHWRegIndex(Reg);
int MaxUsed = HWReg + Width - 1;
if (IsSGPR) {
MaxSGPR = MaxUsed > MaxSGPR ? MaxUsed : MaxSGPR;
} else if (IsAGPR) {
MaxAGPR = MaxUsed > MaxAGPR ? MaxUsed : MaxAGPR;
} else {
MaxVGPR = MaxUsed > MaxVGPR ? MaxUsed : MaxVGPR;
}
}

if (MI.isCall()) {
// Pseudo used just to encode the underlying global. Is there a better
// way to track this?
Expand Down Expand Up @@ -464,9 +219,5 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage(
}
}

Info.NumExplicitSGPR = MaxSGPR + 1;
Info.NumVGPR = MaxVGPR + 1;
Info.NumAGPR = MaxAGPR + 1;

return Info;
}
15 changes: 15 additions & 0 deletions llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -970,10 +970,25 @@ class SIMachineFunctionInfo final : public AMDGPUMachineFunction,
return NumUserSGPRs;
}

// Get the number of preloaded SGPRs for compute kernels.
unsigned getNumPreloadedSGPRs() const {
return NumUserSGPRs + NumSystemSGPRs;
}

// Get the number of preloaded VGPRs for compute kernels.
unsigned getNumPreloadedVGPRs() const {
if (hasWorkItemIDZ())
return ArgInfo.WorkItemIDZ.getRegister() - AMDGPU::VGPR0 + 1;

if (hasWorkItemIDY())
return ArgInfo.WorkItemIDY.getRegister() - AMDGPU::VGPR0 + 1;

if (hasWorkItemIDX())
return ArgInfo.WorkItemIDX.getRegister() - AMDGPU::VGPR0 + 1;

return 0;
}

unsigned getNumKernargPreloadedSGPRs() const {
return UserSGPRInfo.getNumKernargPreloadSGPRs();
}
Expand Down
Loading
Loading