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
| //===--------------------- SummaryView.h ---------------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
/// \file
///
/// This file implements the summary view.
///
/// The goal of the summary view is to give a very quick overview of the
/// performance throughput. Below is an example of summary view:
///
///
/// Iterations: 300
/// Instructions: 900
/// Total Cycles: 610
/// Dispatch Width: 2
/// IPC: 1.48
/// Block RThroughput: 2.0
///
/// The summary view collects a few performance numbers. The two main
/// performance indicators are 'Total Cycles' and IPC (Instructions Per Cycle).
///
//===----------------------------------------------------------------------===//
#ifndef LLVM_TOOLS_LLVM_MCA_SUMMARYVIEW_H
#define LLVM_TOOLS_LLVM_MCA_SUMMARYVIEW_H
#include "Views/View.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/MC/MCSchedule.h"
#include "llvm/Support/raw_ostream.h"
namespace llvm {
namespace mca {
/// A view that collects and prints a few performance numbers.
class SummaryView : public View {
const llvm::MCSchedModel &SM;
llvm::ArrayRef<llvm::MCInst> Source;
const unsigned DispatchWidth;
unsigned LastInstructionIdx;
unsigned TotalCycles;
// The total number of micro opcodes contributed by a block of instructions.
unsigned NumMicroOps;
// For each processor resource, this vector stores the cumulative number of
// resource cycles consumed by the analyzed code block.
llvm::SmallVector<unsigned, 8> ProcResourceUsage;
// Each processor resource is associated with a so-called processor resource
// mask. This vector allows to correlate processor resource IDs with processor
// resource masks. There is exactly one element per each processor resource
// declared by the scheduling model.
llvm::SmallVector<uint64_t, 8> ProcResourceMasks;
// Used to map resource indices to actual processor resource IDs.
llvm::SmallVector<unsigned, 8> ResIdx2ProcResID;
// Compute the reciprocal throughput for the analyzed code block.
// The reciprocal block throughput is computed as the MAX between:
// - NumMicroOps / DispatchWidth
// - Total Resource Cycles / #Units (for every resource consumed).
double getBlockRThroughput() const;
public:
SummaryView(const llvm::MCSchedModel &Model, llvm::ArrayRef<llvm::MCInst> S,
unsigned Width);
void onCycleEnd() override { ++TotalCycles; }
void onEvent(const HWInstructionEvent &Event) override;
void printView(llvm::raw_ostream &OS) const override;
};
} // namespace mca
} // namespace llvm
#endif
|