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
|
//===--------------------- SummaryView.cpp -------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
/// \file
///
/// This file implements the functionalities used by the SummaryView to print
/// the report information.
///
//===----------------------------------------------------------------------===//
#include "Views/SummaryView.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/MCA/Support.h"
#include "llvm/Support/Format.h"
namespace llvm {
namespace mca {
#define DEBUG_TYPE "llvm-mca"
SummaryView::SummaryView(const MCSchedModel &Model, ArrayRef<MCInst> S,
unsigned Width)
: SM(Model), Source(S), DispatchWidth(Width), LastInstructionIdx(0),
TotalCycles(0), NumMicroOps(0),
ProcResourceUsage(Model.getNumProcResourceKinds(), 0),
ProcResourceMasks(Model.getNumProcResourceKinds()) {
computeProcResourceMasks(SM, ProcResourceMasks);
}
void SummaryView::onEvent(const HWInstructionEvent &Event) {
if (Event.Type == HWInstructionEvent::Dispatched)
LastInstructionIdx = Event.IR.getSourceIndex();
// We are only interested in the "instruction retired" events generated by
// the retire stage for instructions that are part of iteration #0.
if (Event.Type != HWInstructionEvent::Retired ||
Event.IR.getSourceIndex() >= Source.size())
return;
// Update the cumulative number of resource cycles based on the processor
// resource usage information available from the instruction descriptor. We
// need to compute the cumulative number of resource cycles for every
// processor resource which is consumed by an instruction of the block.
const Instruction &Inst = *Event.IR.getInstruction();
const InstrDesc &Desc = Inst.getDesc();
NumMicroOps += Desc.NumMicroOps;
for (const std::pair<uint64_t, const ResourceUsage> &RU : Desc.Resources) {
if (RU.second.size()) {
const auto It = find(ProcResourceMasks, RU.first);
assert(It != ProcResourceMasks.end() &&
"Invalid processor resource mask!");
ProcResourceUsage[std::distance(ProcResourceMasks.begin(), It)] +=
RU.second.size();
}
}
}
void SummaryView::printView(raw_ostream &OS) const {
unsigned Instructions = Source.size();
unsigned Iterations = (LastInstructionIdx / Instructions) + 1;
unsigned TotalInstructions = Instructions * Iterations;
unsigned TotalUOps = NumMicroOps * Iterations;
double IPC = (double)TotalInstructions / TotalCycles;
double UOpsPerCycle = (double)TotalUOps / TotalCycles;
double BlockRThroughput = computeBlockRThroughput(
SM, DispatchWidth, NumMicroOps, ProcResourceUsage);
std::string Buffer;
raw_string_ostream TempStream(Buffer);
TempStream << "Iterations: " << Iterations;
TempStream << "\nInstructions: " << TotalInstructions;
TempStream << "\nTotal Cycles: " << TotalCycles;
TempStream << "\nTotal uOps: " << TotalUOps << '\n';
TempStream << "\nDispatch Width: " << DispatchWidth;
TempStream << "\nuOps Per Cycle: "
<< format("%.2f", floor((UOpsPerCycle * 100) + 0.5) / 100);
TempStream << "\nIPC: "
<< format("%.2f", floor((IPC * 100) + 0.5) / 100);
TempStream << "\nBlock RThroughput: "
<< format("%.1f", floor((BlockRThroughput * 10) + 0.5) / 10)
<< '\n';
TempStream.flush();
OS << Buffer;
}
} // namespace mca.
} // namespace llvm
|
