1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
|
//===-- NVPTXTargetTransformInfo.cpp - NVPTX specific TTI -----------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "NVPTXTargetTransformInfo.h"
#include "NVPTXUtilities.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/Support/Debug.h"
#include "llvm/Target/CostTable.h"
#include "llvm/Target/TargetLowering.h"
using namespace llvm;
#define DEBUG_TYPE "NVPTXtti"
// Whether the given intrinsic reads threadIdx.x/y/z.
static bool readsThreadIndex(const IntrinsicInst *II) {
switch (II->getIntrinsicID()) {
default: return false;
case Intrinsic::nvvm_read_ptx_sreg_tid_x:
case Intrinsic::nvvm_read_ptx_sreg_tid_y:
case Intrinsic::nvvm_read_ptx_sreg_tid_z:
return true;
}
}
static bool readsLaneId(const IntrinsicInst *II) {
return II->getIntrinsicID() == Intrinsic::ptx_read_laneid;
}
// Whether the given intrinsic is an atomic instruction in PTX.
static bool isNVVMAtomic(const IntrinsicInst *II) {
switch (II->getIntrinsicID()) {
default: return false;
case Intrinsic::nvvm_atomic_load_add_f32:
case Intrinsic::nvvm_atomic_load_inc_32:
case Intrinsic::nvvm_atomic_load_dec_32:
return true;
}
}
bool NVPTXTTIImpl::isSourceOfDivergence(const Value *V) {
// Without inter-procedural analysis, we conservatively assume that arguments
// to __device__ functions are divergent.
if (const Argument *Arg = dyn_cast<Argument>(V))
return !isKernelFunction(*Arg->getParent());
if (const Instruction *I = dyn_cast<Instruction>(V)) {
// Without pointer analysis, we conservatively assume values loaded from
// generic or local address space are divergent.
if (const LoadInst *LI = dyn_cast<LoadInst>(I)) {
unsigned AS = LI->getPointerAddressSpace();
return AS == ADDRESS_SPACE_GENERIC || AS == ADDRESS_SPACE_LOCAL;
}
// Atomic instructions may cause divergence. Atomic instructions are
// executed sequentially across all threads in a warp. Therefore, an earlier
// executed thread may see different memory inputs than a later executed
// thread. For example, suppose *a = 0 initially.
//
// atom.global.add.s32 d, [a], 1
//
// returns 0 for the first thread that enters the critical region, and 1 for
// the second thread.
if (I->isAtomic())
return true;
if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(I)) {
// Instructions that read threadIdx are obviously divergent.
if (readsThreadIndex(II) || readsLaneId(II))
return true;
// Handle the NVPTX atomic instrinsics that cannot be represented as an
// atomic IR instruction.
if (isNVVMAtomic(II))
return true;
}
// Conservatively consider the return value of function calls as divergent.
// We could analyze callees with bodies more precisely using
// inter-procedural analysis.
if (isa<CallInst>(I))
return true;
}
return false;
}
unsigned NVPTXTTIImpl::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, TTI::OperandValueKind Opd1Info,
TTI::OperandValueKind Opd2Info, TTI::OperandValueProperties Opd1PropInfo,
TTI::OperandValueProperties Opd2PropInfo) {
// Legalize the type.
std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Ty);
int ISD = TLI->InstructionOpcodeToISD(Opcode);
switch (ISD) {
default:
return BaseT::getArithmeticInstrCost(Opcode, Ty, Opd1Info, Opd2Info,
Opd1PropInfo, Opd2PropInfo);
case ISD::ADD:
case ISD::MUL:
case ISD::XOR:
case ISD::OR:
case ISD::AND:
// The machine code (SASS) simulates an i64 with two i32. Therefore, we
// estimate that arithmetic operations on i64 are twice as expensive as
// those on types that can fit into one machine register.
if (LT.second.SimpleTy == MVT::i64)
return 2 * LT.first;
// Delegate other cases to the basic TTI.
return BaseT::getArithmeticInstrCost(Opcode, Ty, Opd1Info, Opd2Info,
Opd1PropInfo, Opd2PropInfo);
}
}
|
