SIWholeQuadMode.cpp File Reference

This pass adds instructions to enable whole quad mode for pixel shaders, and whole wavefront mode for all programs. More...

#include "AMDGPU.h"
#include "AMDGPUSubtarget.h"
#include "SIInstrInfo.h"
#include "SIMachineFunctionInfo.h"
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/PostOrderIterator.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/CodeGen/LiveInterval.h"
#include "llvm/CodeGen/LiveIntervals.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineOperand.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/SlotIndexes.h"
#include "llvm/CodeGen/TargetRegisterInfo.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/IR/DebugLoc.h"
#include "llvm/MC/MCRegisterInfo.h"
#include "llvm/Pass.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include <cassert>
#include <vector>

Include dependency graph for SIWholeQuadMode.cpp:

Go to the source code of this file.

Macros
#define	DEBUG_TYPE   "si-wqm"

Enumerations
enum

Functions
	INITIALIZE_PASS_BEGIN (SIWholeQuadMode, DEBUG_TYPE, "SI Whole Quad Mode", false, false) INITIALIZE_PASS_END(SIWholeQuadMode

Variables
	DEBUG_TYPE
SI Whole Quad	Mode
SI Whole Quad	false

Detailed Description

This pass adds instructions to enable whole quad mode for pixel shaders, and whole wavefront mode for all programs.

Whole quad mode is required for derivative computations, but it interferes with shader side effects (stores and atomics). This pass is run on the scheduled machine IR but before register coalescing, so that machine SSA is available for analysis. It ensures that WQM is enabled when necessary, but disabled around stores and atomics.

When necessary, this pass creates a function prolog

S_MOV_B64 LiveMask, EXEC S_WQM_B64 EXEC, EXEC

to enter WQM at the top of the function and surrounds blocks of Exact instructions by

S_AND_SAVEEXEC_B64 Tmp, LiveMask ... S_MOV_B64 EXEC, Tmp

We also compute when a sequence of instructions requires Whole Wavefront Mode (WWM) and insert instructions to save and restore it:

S_OR_SAVEEXEC_B64 Tmp, -1 ... S_MOV_B64 EXEC, Tmp

In order to avoid excessive switching during sequences of Exact instructions, the pass first analyzes which instructions must be run in WQM (aka which instructions produce values that lead to derivative computations).

Basic blocks are always exited in WQM as long as some successor needs WQM.

There is room for improvement given better control flow analysis:

(1) at the top level (outside of control flow statements, and as long as kill hasn't been used), one SGPR can be saved by recovering WQM from the LiveMask (this is implemented for the entry block).

(2) when entire regions (e.g. if-else blocks or entire loops) only consist of exact and don't-care instructions, the switch only has to be done at the entry and exit points rather than potentially in each block of the region.

Definition in file SIWholeQuadMode.cpp.

Macro Definition Documentation

DEBUG_TYPE

#define DEBUG_TYPE   "si-wqm"

Definition at line 90 of file SIWholeQuadMode.cpp.

Enumeration Type Documentation

anonymous enum

anonymous enum

Definition at line 94 of file SIWholeQuadMode.cpp.

Function Documentation

INITIALIZE_PASS_BEGIN()

INITIALIZE_PASS_BEGIN	(	SIWholeQuadMode	,
		DEBUG_TYPE	,
		"SI Whole Quad Mode"	,
		false	,
		false
	)

Variable Documentation

DEBUG_TYPE

DEBUG_TYPE

Definition at line 216 of file SIWholeQuadMode.cpp.

false

SI Whole Quad false

Definition at line 216 of file SIWholeQuadMode.cpp.

Mode

SI Whole Quad Mode

Definition at line 216 of file SIWholeQuadMode.cpp.

Referenced by llvm::AAResults::canBasicBlockModify(), combineLoopMAddPattern(), ContainsReg(), llvm::FileOutputBuffer::create(), createInMemoryBuffer(), llvm::createSIModeRegisterPass(), findIncDecAfter(), llvm::raw_ostream::getBufferStart(), llvm::TGParser::getDependencies(), getLAScore(), INITIALIZE_PASS(), llvm::IsCPSRDead< MCInst >(), isIndirectBrTarget(), isMemberPointer(), isWeak(), matchPMADDWD(), llvm::ARMInstPrinter::printLdStmModeOperand(), reduceVMULWidth(), llvm::HexagonMCChecker::reportBranchErrors(), llvm::raw_ostream::SetBuffered(), llvm::TargetMachine::setGlobalISelAbort(), shouldEmitUdt(), tieOpsIfNeeded(), and llvm::AntiDepBreaker::~AntiDepBreaker().