forked from OSchip/llvm-project
[AMDGPU] Revert "[AMDGPU] Add options for waitcnt pass debugging; add instr count in debug output."
Patch caused a buildbot failure; http://lab.llvm.org:8011/builders/lld-x86_64-darwin13/builds/15733/steps/build_Lld/logs/stdio : lib/Target/AMDGPU/SIInsertWaitcnts.cpp:396:11: error: private field 'InstCnt' is not used [-Werror,-Wunused-private-field] int32_t InstCnt = 0; ^ 1 error generated. " This reverts commit 71627f79010aafe74fdcba901bba28dd7caa0869. llvm-svn: 320086
This commit is contained in:
Mark Searles
parent
690f0e2f4e
commit
9ebdbb433a
|
|
@ -54,26 +54,6 @@
|
|||
|
||||
using namespace llvm;
|
||||
|
||||
static cl::opt<unsigned> ForceZeroFlag(
|
||||
"amdgpu-waitcnt-forcezero",
|
||||
cl::desc("Force all waitcnt instrs to be emitted as s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)"),
|
||||
cl::init(0), cl::Hidden);
|
||||
|
||||
static cl::opt<unsigned> ForceExpFlag(
|
||||
"amdgpu-waitcnt-forceexp",
|
||||
cl::desc("Force emit a s_waitcnt expcnt(0) before the first <n> instrs"),
|
||||
cl::init(0), cl::Hidden);
|
||||
|
||||
static cl::opt<unsigned> ForceLgkmFlag(
|
||||
"amdgpu-waitcnt-forcelgkm",
|
||||
cl::desc("Force emit a s_waitcnt lgkmcnt(0) before the first <n> instrs"),
|
||||
cl::init(0), cl::Hidden);
|
||||
|
||||
static cl::opt<unsigned> ForceVmFlag(
|
||||
"amdgpu-waitcnt-forcevm",
|
||||
cl::desc("Force emit a s_waitcnt vmcnt(0) before the first <n> instrs"),
|
||||
cl::init(0), cl::Hidden);
|
||||
|
||||
namespace {
|
||||
|
||||
// Class of object that encapsulates latest instruction counter score
|
||||
|
|
@ -393,10 +373,6 @@ private:
|
|||
|
||||
std::vector<std::unique_ptr<BlockWaitcntBrackets>> KillWaitBrackets;
|
||||
|
||||
int32_t InstCnt = 0;
|
||||
bool ForceZero = false;
|
||||
int32_t ForceSwaitcnt[NUM_INST_CNTS];
|
||||
|
||||
public:
|
||||
static char ID;
|
||||
|
||||
|
|
@ -421,14 +397,6 @@ public:
|
|||
llvm::make_unique<BlockWaitcntBrackets>(*Bracket));
|
||||
}
|
||||
|
||||
bool ForceEmit() const {
|
||||
for (enum InstCounterType T = VM_CNT; T < NUM_INST_CNTS;
|
||||
T = (enum InstCounterType)(T + 1))
|
||||
if (ForceSwaitcnt[T] > 0)
|
||||
return true;
|
||||
return false;
|
||||
}
|
||||
|
||||
bool mayAccessLDSThroughFlat(const MachineInstr &MI) const;
|
||||
MachineInstr *generateSWaitCntInstBefore(MachineInstr &MI,
|
||||
BlockWaitcntBrackets *ScoreBrackets);
|
||||
|
|
@ -1055,6 +1023,9 @@ MachineInstr *SIInsertWaitcnts::generateSWaitCntInstBefore(
|
|||
} // End of for loop that looks at all dest operands.
|
||||
}
|
||||
|
||||
// TODO: Tie force zero to a compiler triage option.
|
||||
bool ForceZero = false;
|
||||
|
||||
// Check to see if this is an S_BARRIER, and if an implicit S_WAITCNT 0
|
||||
// occurs before the instruction. Doing it here prevents any additional
|
||||
// S_WAITCNTs from being emitted if the instruction was marked as
|
||||
|
|
@ -1087,7 +1058,7 @@ MachineInstr *SIInsertWaitcnts::generateSWaitCntInstBefore(
|
|||
}
|
||||
|
||||
// Does this operand processing indicate s_wait counter update?
|
||||
if (EmitSwaitcnt || ForceEmit()) {
|
||||
if (EmitSwaitcnt) {
|
||||
int CntVal[NUM_INST_CNTS];
|
||||
|
||||
bool UseDefaultWaitcntStrategy = true;
|
||||
|
|
@ -1128,7 +1099,7 @@ MachineInstr *SIInsertWaitcnts::generateSWaitCntInstBefore(
|
|||
}
|
||||
|
||||
// If we are not waiting on any counter we can skip the wait altogether.
|
||||
if (EmitSwaitcnt != 0 || ForceEmit()) {
|
||||
if (EmitSwaitcnt != 0) {
|
||||
MachineInstr *OldWaitcnt = ScoreBrackets->getWaitcnt();
|
||||
int Imm = (!OldWaitcnt) ? 0 : OldWaitcnt->getOperand(0).getImm();
|
||||
if (!OldWaitcnt || (AMDGPU::decodeVmcnt(IV, Imm) !=
|
||||
|
|
@ -1164,31 +1135,11 @@ MachineInstr *SIInsertWaitcnts::generateSWaitCntInstBefore(
|
|||
CompilerGeneratedWaitcntSet.insert(SWaitInst);
|
||||
}
|
||||
|
||||
if (!EmitSwaitcnt) {
|
||||
for (enum InstCounterType T = VM_CNT; T < NUM_INST_CNTS;
|
||||
T = (enum InstCounterType)(T + 1)) {
|
||||
if (ForceSwaitcnt[T] > 0 ) {
|
||||
DEBUG(dbgs() << "ForceSwaitcnt[" << T << "]: "
|
||||
<< ForceSwaitcnt[T] << '\n';);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const MachineOperand &Op =
|
||||
MachineOperand::CreateImm(AMDGPU::encodeWaitcnt(
|
||||
IV,
|
||||
(ForceSwaitcnt[VM_CNT] > 0) ? 0 : CntVal[VM_CNT],
|
||||
(ForceSwaitcnt[EXP_CNT] > 0) ? 0 : CntVal[EXP_CNT],
|
||||
(ForceSwaitcnt[LGKM_CNT] > 0) ? 0 : CntVal[LGKM_CNT]));
|
||||
IV, CntVal[VM_CNT], CntVal[EXP_CNT], CntVal[LGKM_CNT]));
|
||||
SWaitInst->addOperand(MF, Op);
|
||||
|
||||
if (!EmitSwaitcnt) {
|
||||
for (enum InstCounterType T = VM_CNT; T < NUM_INST_CNTS;
|
||||
T = (enum InstCounterType)(T + 1)) {
|
||||
--ForceSwaitcnt[T];
|
||||
}
|
||||
}
|
||||
|
||||
if (CntVal[EXP_CNT] == 0) {
|
||||
ScoreBrackets->setMixedExpTypes(false);
|
||||
}
|
||||
|
|
@ -1567,7 +1518,7 @@ void SIInsertWaitcnts::insertWaitcntInBlock(MachineFunction &MF,
|
|||
BlockWaitcntBrackets *ScoreBrackets = BlockWaitcntBracketsMap[&Block].get();
|
||||
|
||||
DEBUG({
|
||||
dbgs() << "*** Block" << Block.getNumber() << " ***";
|
||||
dbgs() << "Block" << Block.getNumber();
|
||||
ScoreBrackets->dump();
|
||||
});
|
||||
|
||||
|
|
@ -1640,7 +1591,7 @@ void SIInsertWaitcnts::insertWaitcntInBlock(MachineFunction &MF,
|
|||
DEBUG({ SWaitInst->print(dbgs() << '\n'); });
|
||||
}
|
||||
DEBUG({
|
||||
dbgs() << "Instr" << ++InstCnt << ": " << Inst;
|
||||
Inst.print(dbgs());
|
||||
ScoreBrackets->dump();
|
||||
});
|
||||
|
||||
|
|
@ -1745,11 +1696,6 @@ bool SIInsertWaitcnts::runOnMachineFunction(MachineFunction &MF) {
|
|||
const SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
|
||||
AMDGPUASI = ST->getAMDGPUAS();
|
||||
|
||||
ForceZero = ForceZeroFlag;
|
||||
ForceSwaitcnt[VM_CNT] = ForceVmFlag;
|
||||
ForceSwaitcnt[EXP_CNT] = ForceExpFlag;
|
||||
ForceSwaitcnt[LGKM_CNT] = ForceLgkmFlag;
|
||||
|
||||
HardwareLimits.VmcntMax = AMDGPU::getVmcntBitMask(IV);
|
||||
HardwareLimits.ExpcntMax = AMDGPU::getExpcntBitMask(IV);
|
||||
HardwareLimits.LgkmcntMax = AMDGPU::getLgkmcntBitMask(IV);
|
||||
|
|
|
|||
|
|
@ -1,41 +0,0 @@
|
|||
# RUN: llc -mtriple=amdgcn -verify-machineinstrs -run-pass si-insert-waitcnts -amdgpu-waitcnt-forcelgkm=1 -o - %s | FileCheck -check-prefixes=GCN,LGKM %s
|
||||
# RUN: llc -mtriple=amdgcn -verify-machineinstrs -run-pass si-insert-waitcnts -amdgpu-waitcnt-forceexp=2 -o - %s | FileCheck -check-prefixes=GCN,EXP %s
|
||||
# RUN: llc -mtriple=amdgcn -verify-machineinstrs -run-pass si-insert-waitcnts -amdgpu-waitcnt-forcevm=3 -o - %s | FileCheck -check-prefixes=GCN,VM %s
|
||||
# RUN: llc -mtriple=amdgcn -verify-machineinstrs -run-pass si-insert-waitcnts -amdgpu-waitcnt-forcezero=1 -amdgpu-waitcnt-forcevm=2 -o - %s | FileCheck -check-prefixes=GCN,ZERO %s
|
||||
|
||||
# check that the waitcnt pass options that force insertion of waitcnt instructions are working as expected
|
||||
|
||||
...
|
||||
# GCN-LABEL: name: waitcnt-debug
|
||||
# LGKM: S_WAITCNT 127
|
||||
# LGKM-NEXT: S_NOP 0
|
||||
# LGKM-NEXT: S_NOP 0
|
||||
|
||||
# EXP: S_WAITCNT 3855
|
||||
# EXP-NEXT: S_NOP 0
|
||||
# EXP-NEXT: S_WAITCNT 3855
|
||||
# EXP-NEXT: S_NOP 0
|
||||
|
||||
# VM: S_WAITCNT 3952
|
||||
# VM-NEXT: S_NOP 0
|
||||
# VM-NEXT: S_WAITCNT 3952
|
||||
# VM-NEXT: S_NOP 0
|
||||
# VM-NEXT: S_WAITCNT 3952
|
||||
# VM-NEXT: S_NOP 0
|
||||
|
||||
# ZERO: S_WAITCNT 0
|
||||
# ZERO-NEXT: S_WAITCNT 0
|
||||
# ZERO-NEXT: S_NOP 0
|
||||
# ZERO-NEXT: S_WAITCNT 0
|
||||
# ZERO-NEXT: S_NOP 0
|
||||
|
||||
name: waitcnt-debug
|
||||
liveins:
|
||||
body: |
|
||||
bb.0:
|
||||
S_NOP 0
|
||||
S_NOP 0
|
||||
S_NOP 0
|
||||
S_NOP 0
|
||||
...
|
||||
|
||||
Loading…
Reference in New Issue