CodegenAnalysis.Assertions 0.1.0-alpha-1659621383-f874603

CodegenAnalysis

⚠️ The library is in progress (alpha versioning).

⚠️ No expected behaviour, no documentation, no backward compatibility.

<img align="right" src="./logo1t.png" width=200>

Library for analyzing the machine code generated by JIT (codegen). Has API for obtaining the codegen, verifying the characteristics for tests (in a similar manner to xUnit), and generating reports as benchmarks (in a similar manner to BenchmarkDotNet). Supports x86_64 on three major platforms (Windows, MacOS, Linux).

Why should I use it?

First of all, most .NET developers don't need this library. If you want to measure performance of your code, use BenchmarkDotNet.

If you're working on low-level, often HW-related project, where it's crucial if a branch or call or etc. is optimized or not, this library is for you.

Table of contents

• CodegenAnalysis
• CodegenAnalysis.Assertions
• CodegenAnalysis.Benchmarks

CodegenAnalysis

static int AddAndMul(int a, int b) => a + b * a;

...

var ci = CodegenInfo.Obrain(() => AddAndMul(3, 5));
Console.WriteLine(ci);

Output:

00007FFD752E42F0 8BC2                 mov       eax,edx
00007FFD752E42F2 0FAFC1               imul      eax,ecx
00007FFD752E42F5 03C1                 add       eax,ecx
00007FFD752E42F7 C3                   ret

CodegenAnalysis.Assertions

Verifying the size of the codegen

using CodegenAssertions;
using Xunit;

public class CodegenSizeTest
{
    public static int SomeMethod(int a, int b)
        => a + b;

    [Fact]
    public void Test1()
    {
        CodegenInfo.Obtain(() => SomeMethod(4, 5), CompilationTier.Tier1)
            .ShouldBeNotLargerThan(20);
    }
}

Having calls in the codegen

public class Tests
{
    public class A
    {
        public virtual int H => 3;
    }

    public sealed class B : A
    {
        public override int H => 6;
    }

    // this will get devirtualized at tier1, but not at tier0
    static int Twice(B b) => b.H * 2;

    [Fact]
    public void NotDevirtTier0()
    {
        CodegenInfo.Obtain(() => Twice(new B()), CompilationTier.Default)
            .ShouldHaveCalls(c => c >= 1);
    }

    [Fact]
    public void DevirtTier1()
    {
        CodegenInfo.Obtain(() => Twice(new B()), CompilationTier.Tier1)
            .ShouldHaveCalls(0);
    }
}

Testing if we have branches

    private static readonly bool True = true;

    static int SmartThing()
    {
        if (True)
            return 5;
        return 10;
    }

    [Fact]
    public void BranchElimination()
    {
        CodegenInfo.Obtain(() => SmartThing())
            .ShouldHaveBranches(0);
    }

    [MethodImpl(MethodImplOptions.NoOptimization)]
    static int StupidThing()
    {
        if (True)
            return 5;
        return 10;
    }

    [Fact]
    public void NoBranchElimination()
    {
        CodegenInfo.Obtain(() => StupidThing(), CompilationTier.Default)
            .ShouldHaveBranches(b => b > 0);
    }

CodegenAnalysis.Benchmarks

CodegenBenchmarkRunner.Run<A>();

[CAJob(Tier = CompilationTier.Default),
 CAJob(Tier = CompilationTier.Tier1)]

[CAColumn(CAColumn.Branches),
 CAColumn(CAColumn.Calls), 
 CAColumn(CAColumn.CodegenSize), 
 CAColumn(CAColumn.StaticStackAllocations)]

[CAExport(Export.Html),
 CAExport(Export.Md)]
public class A
{
    [CAAnalyze(3.5f)]
    [CAAnalyze(13.5f)]
    public static float Heavy(float a)
    {
        var b = Do1(a);
        var c = Do1(b);
        if (a > 10)
            c += Aaa(a);
        return c + b;


    [CAAnalyze(6f)]
    public static float Square(float a)
    {
        return a * a;
    }

    [MethodImpl(MethodImplOptions.NoInlining)]
    public static float Do1(float a)
    {
        return a * 2;
    }

    [MethodImpl(MethodImplOptions.NoInlining)]
    public static float Aaa(float h)
    {
        return h * h * h;
    }
}

Output in markdown (with these Export attributes you will see html and plain output in CodegenAnalysis.Artifacts):

Codegen analysis report

2022-08-04 13:49 UTC

Summary

Codegens

Single Heavy(Single): Default

  00007F2131C20570 55                   push      rbp
  00007F2131C20571 4883EC10             sub       rsp,10h
  00007F2131C20575 C5F877               vzeroupper
  00007F2131C20578 488D6C2410           lea       rbp,[rsp+10h]
  00007F2131C2057D 33C0                 xor       eax,eax
  00007F2131C2057F 8945F8               mov       [rbp-8],eax
  00007F2131C20582 8945F4               mov       [rbp-0Ch],eax
  00007F2131C20585 C5FA1145FC           vmovss    [rbp-4],xmm0
  00007F2131C2058A C5FA1045FC           vmovss    xmm0,[rbp-4]
  00007F2131C2058F E8341FB4FF           call      Single Do1(Single) (00007F21317624C8)
  00007F2131C20594 C5FA1145F8           vmovss    [rbp-8],xmm0
  00007F2131C20599 C5FA1045F8           vmovss    xmm0,[rbp-8]
  00007F2131C2059E E8251FB4FF           call      Single Do1(Single) (00007F21317624C8)
  00007F2131C205A3 C5FA1145F4           vmovss    [rbp-0Ch],xmm0
  00007F2131C205A8 C5FA1045FC           vmovss    xmm0,[rbp-4]
  00007F2131C205AD C5F82E0533000000     vucomiss  xmm0,[rel 7F21`31C2`05E8h]
┌─00007F2131C205B5 7614                 jbe       short 0000`7F21`31C2`05CBh
│ 00007F2131C205B7 C5FA1045FC           vmovss    xmm0,[rbp-4]
│ 00007F2131C205BC E80F1FB4FF           call      0000`7F21`3176`24D0h
│ 00007F2131C205C1 C5FA5845F4           vaddss    xmm0,xmm0,[rbp-0Ch]
│ 00007F2131C205C6 C5FA1145F4           vmovss    [rbp-0Ch],xmm0
└>00007F2131C205CB C5FA1045F4           vmovss    xmm0,[rbp-0Ch]
  00007F2131C205D0 C5FA5845F8           vaddss    xmm0,xmm0,[rbp-8]
  00007F2131C205D5 4883C410             add       rsp,10h
  00007F2131C205D9 5D                   pop       rbp
  00007F2131C205DA C3                   ret

Single Heavy(Single): Tier1

  00007F2131C3E290 55                   push      rbp
  00007F2131C3E291 4883EC10             sub       rsp,10h
  00007F2131C3E295 C5F877               vzeroupper
  00007F2131C3E298 488D6C2410           lea       rbp,[rsp+10h]
  00007F2131C3E29D C5FA1145FC           vmovss    [rbp-4],xmm0
  00007F2131C3E2A2 E82142B2FF           call      Single Do1(Single) (00007F21317624C8)
  00007F2131C3E2A7 C5FA1145F8           vmovss    [rbp-8],xmm0
  00007F2131C3E2AC E81742B2FF           call      Single Do1(Single) (00007F21317624C8)
  00007F2131C3E2B1 C5FA1145F4           vmovss    [rbp-0Ch],xmm0
  00007F2131C3E2B6 C5FA104DFC           vmovss    xmm1,[rbp-4]
  00007F2131C3E2BB C5F82E0D35000000     vucomiss  xmm1,[rel 7F21`31C3`E2F8h]
┌─00007F2131C3E2C3 7613                 jbe       short 0000`7F21`31C3`E2D8h
│ 00007F2131C3E2C5 C5F828C1             vmovaps   xmm0,xmm1
│ 00007F2131C3E2C9 E80242B2FF           call      0000`7F21`3176`24D0h
│ 00007F2131C3E2CE C5FA5845F4           vaddss    xmm0,xmm0,[rbp-0Ch]
│ 00007F2131C3E2D3 C5FA1145F4           vmovss    [rbp-0Ch],xmm0
└>00007F2131C3E2D8 C5FA1045F4           vmovss    xmm0,[rbp-0Ch]
  00007F2131C3E2DD C5FA5845F8           vaddss    xmm0,xmm0,[rbp-8]
  00007F2131C3E2E2 4883C410             add       rsp,10h
  00007F2131C3E2E6 5D                   pop       rbp
  00007F2131C3E2E7 C3                   ret

Single Square(Single): Default

00007F2131C3C2F0 55                   push      rbp
00007F2131C3C2F1 4883EC10             sub       rsp,10h
00007F2131C3C2F5 C5F877               vzeroupper
00007F2131C3C2F8 488D6C2410           lea       rbp,[rsp+10h]
00007F2131C3C2FD C5FA1145FC           vmovss    [rbp-4],xmm0
00007F2131C3C302 C5FA1045FC           vmovss    xmm0,[rbp-4]
00007F2131C3C307 C5FA5945FC           vmulss    xmm0,xmm0,[rbp-4]
00007F2131C3C30C 4883C410             add       rsp,10h
00007F2131C3C310 5D                   pop       rbp
00007F2131C3C311 C3                   ret

Single Square(Single): Tier1

00007F2131C475A0 C5F877               vzeroupper
00007F2131C475A3 C5FA59C0             vmulss    xmm0,xmm0,xmm0
00007F2131C475A7 C3                   ret