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
|
//===--------------------- ResourcePressureView.h ---------------*- 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 define class ResourcePressureView.
/// Class ResourcePressureView observes hardware events generated by
/// the Pipeline object and collects statistics related to resource usage at
/// instruction granularity.
/// Resource pressure information is then printed out to a stream in the
/// form of a table like the one from the example below:
///
/// Resources:
/// [0] - JALU0
/// [1] - JALU1
/// [2] - JDiv
/// [3] - JFPM
/// [4] - JFPU0
/// [5] - JFPU1
/// [6] - JLAGU
/// [7] - JSAGU
/// [8] - JSTC
/// [9] - JVIMUL
///
/// Resource pressure per iteration:
/// [0] [1] [2] [3] [4] [5] [6] [7] [8] [9]
/// 0.00 0.00 0.00 0.00 2.00 2.00 0.00 0.00 0.00 0.00
///
/// Resource pressure by instruction:
/// [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] Instructions:
/// - - - - - 1.00 - - - - vpermilpd $1, %xmm0,
/// %xmm1
/// - - - - 1.00 - - - - - vaddps %xmm0, %xmm1,
/// %xmm2
/// - - - - - 1.00 - - - - vmovshdup %xmm2, %xmm3
/// - - - - 1.00 - - - - - vaddss %xmm2, %xmm3,
/// %xmm4
///
/// In this example, we have AVX code executed on AMD Jaguar (btver2).
/// Both shuffles and vector floating point add operations on XMM registers have
/// a reciprocal throughput of 1cy.
/// Each add is issued to pipeline JFPU0, while each shuffle is issued to
/// pipeline JFPU1. The overall pressure per iteration is reported by two
/// tables: the first smaller table is the resource pressure per iteration;
/// the second table reports resource pressure per instruction. Values are the
/// average resource cycles consumed by an instruction.
/// Every vector add from the example uses resource JFPU0 for an average of 1cy
/// per iteration. Consequently, the resource pressure on JFPU0 is of 2cy per
/// iteration.
///
//===----------------------------------------------------------------------===//
#ifndef LLVM_TOOLS_LLVM_MCA_RESOURCEPRESSUREVIEW_H
#define LLVM_TOOLS_LLVM_MCA_RESOURCEPRESSUREVIEW_H
#include "Views/View.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/MC/MCInst.h"
#include "llvm/MC/MCInstPrinter.h"
#include "llvm/MC/MCSubtargetInfo.h"
namespace llvm {
namespace mca {
/// This class collects resource pressure statistics and it is able to print
/// out all the collected information as a table to an output stream.
class ResourcePressureView : public View {
const llvm::MCSubtargetInfo &STI;
llvm::MCInstPrinter &MCIP;
llvm::ArrayRef<llvm::MCInst> Source;
unsigned LastInstructionIdx;
// Map to quickly obtain the ResourceUsage column index from a processor
// resource ID.
llvm::DenseMap<unsigned, unsigned> Resource2VecIndex;
// Table of resources used by instructions.
std::vector<ResourceCycles> ResourceUsage;
unsigned NumResourceUnits;
void printResourcePressurePerIter(llvm::raw_ostream &OS) const;
void printResourcePressurePerInst(llvm::raw_ostream &OS) const;
public:
ResourcePressureView(const llvm::MCSubtargetInfo &sti,
llvm::MCInstPrinter &Printer,
llvm::ArrayRef<llvm::MCInst> S);
void onEvent(const HWInstructionEvent &Event) override;
void printView(llvm::raw_ostream &OS) const override {
printResourcePressurePerIter(OS);
printResourcePressurePerInst(OS);
}
};
} // namespace mca
} // namespace llvm
#endif
|
