SlideShare a Scribd company logo
1 of 74
Micro-optimizations
in .NET world
.NET LEVEL UP .NET CONFERENCE #1 IN UKRAINE KYIV 2019
What is micro-optimization
What is micro-optimization
DataController.Get
MyService.GetData
DataRepository.Load
DbCommand.ExecuteRead
MyService.Process
MyService.Calculate
Total time Own timeMethod
15 234 ms
15 221 ms
14 163 ms
14 028 ms
1 034 ms
975 ms
13 ms
24 ms
135 ms
3 ms
59 ms
975 ms
What is micro-optimization
DataController.Get
MyService.GetData
DataRepository.Load
DbCommand.ExecuteRead
MyService.Process
MyService.Calculate
Total time Own timeMethod
15 234 ms
15 221 ms
832 ms
697 ms
14 365 ms
14 227 ms
13 ms
24 ms
135 ms
5 ms
138 ms
14 227 ms
What is micro-optimization
Noun
micro-optimization (plural micro-optimizations)
(programming, computer architecture)

Optimization at the level of individual instructions and operations.
Неделя оптимизации кода
А разговоров-то
было
Intrinsics
Intrinsics
Noun
intrinsic (plural intrinsics)
(computing, programming)
A built-in function that is implemented directly by the compiler,
without any intermediate call to a library.
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
2005
2004
2003
2002
2001
2000
1999
1998
1997
MMX
SSE
3DNow!
SSE2
SSE4
SSSE3
SSE3
ADX
AVX2, BMI2
AVX
FMA4
CLMUL, AES-NI
FMA3, BMI1
AVX-512
PADDW (Add Packed Integers)
x0x1x2x3x4x5x6x7
y0y1y2y3y4y5y6y7
x0+y0x1+y1x2+y2x3+y3x4+y4x5+y5x6+y6x7+y7
Source 1
Source 2
Result
PDEP (Parallel Bits Deposit)
x0x1x2x3x4x5x6x7Source 1
Source 2
Result
00101100
x0x1x2x3x4x5
0010
xn
000
…
…
00x00x1x20000x30000 …
Intrinsics
• SSE, SSE2, SSE3, SSE4, SSE4.1, SSE4.2, SSSE3

• Lzcnt, Popcnt

• AVX, AVX2

• AES

• BMI1, BMI2

• FMA

• CLMUL

• NEON (ARM)
using System.Runtime.Intrinsics.X86;
uint CalculateCrc32(byte[] data)
{
    if (Sse42.IsSupported)
    {
        uint result = 0;
        foreach (var b in data)
            result = Sse42.Crc32(result, b);
        return result;
    }
    else
    {
        // Falback implementation of the method
        // without using intrinsics
    }
}
namespace System.Numerics
{
    public static class BitOperations
    {
        public static int Log2(uint value)
        {
            if (Lzcnt.IsSupported)
            {
                if (value == 0)
                {
                    return 0;
                }
                // LZCNT contract is 0->32
                return 31 - (int)Lzcnt.LeadingZeroCount(value);
            }
            // Fallback contract is 0->0
            return Log2SoftwareFallback(value);
        }
}
}
Benchmark:
| Time |
---------- |--------:|
Lznt | 0.58 ns |
Fallback | 1.52 ns |
Vectorization
byte[] data = ...
for (var i = 0; i < data.Length; i++)
{
    var item = data[i];
    DoAction(item);
}
byte[] data = ...
for (var i = 0; i < data.Length; i += 8)
{
    var vector = data[i..i+8]
    DoAction(vector);
}
Verb
vectorize
(computing, transitive)

To convert a program that operates on scalar values into
the equivalent program operating on vectors.
public static int IndexOf(this ReadOnlySpan<char> source, char value, int startIndex)
{
    for (int i = startIndex; i < source.Length; i++)
    {
        if (source[i] == value)
        {
            return i;
        }
    }
    return -1;
}
public static unsafe int IndexOf(ref char searchSpace, char value, int length)
{
if (Sse2.IsSupported)
        Determine how many to iterate to get data 16 bytes aligned
SequentialScan:
Iterate byte by byte
if (Avx2.IsSupported)
    {
if (not 32 bytes aligned)
Check 16 bytes using SSE2
Iterate by 32 bytes using AVX2
if (more than 16 bytes left)
Check 16 bytes using SSE2
if (not all data iterated)
goto SequentialScan;
    }
    else if (Sse2.IsSupported)
    {
Iterate by 16 bytes using SSE2
if (not all data iterated)
goto SequentialScan:
}
Found:
return offset;
}
Benchmark:
Length | Time |
----- |--------:|-----------:|
Old | 15 | 8.817 ns |
New | 15 | 4.577 ns |
Old | 1024 | 68.530 ns |
New | 1024 | 49.741 ns |
Heap allocations
(almost) New features
• ArrayPool class

• Span and ReadOnlySpan structures

• stackalloc
namespace System
{
    internal static class DateTimeFormat
    {
        internal static string Format(DateTime dateTime, string? format, IFormatProvider? provider, TimeSpan offset)
        {
            if (format != null && format.Length == 1)
            {
                // Optimize for these standard formats that are not affected by culture.
                switch (format[0])
                {
                    // Round trip format
                    case 'o':
                    case 'O':
                        const int MaxFormatOLength = 33;
                        Span<char> span = stackalloc char[MaxFormatOLength];
                        TryFormatO(dateTime, offset, span, out int ochars);
                        return span.Slice(0, ochars).ToString();
                }
            }
// ... More code goes here...
        }
}
}
namespace System.Data.SqlClient
{
    internal sealed partial class TdsParser
{
        private bool TryReadSqlDateTime(SqlBuffer value, byte tdsType, int length, byte scale, TdsParserStateObject stateObj)
        {
            Span<byte> datetimeBuffer = ((uint)length <= 16) ? stackalloc byte[16] : new byte[length];
            if (!stateObj.TryReadByteArray(datetimeBuffer, length))
            {
                return false;
            }
            ReadOnlySpan<byte> dateTimeData = datetimeBuffer.Slice(0, length);
// ... More code goes here...
}
}
}
namespace System.IO
{
    public abstract partial class TextReader : MarshalByRefObject, IDisposable
{
        public virtual async Task<string> ReadToEndAsync()
        {
            var sb = new StringBuilder(4096);
            char[] chars = ArrayPool<char>.Shared.Rent(4096);
            try
            {
                int len;
                while ((len = await ReadAsyncInternal(chars, default).ConfigureAwait(false)) != 0)
                {
                    sb.Append(chars, 0, len);
                }
            }
            finally
            {
                ArrayPool<char>.Shared.Return(chars);
            }
            return sb.ToString();
        }
}
}
namespace System.Text.Json
{
    public static partial class JsonSerializer
    {
        private static ReadOnlySpan<byte> GetUnescapedString(ReadOnlySpan<byte> utf8Source, int idx)
        {
            // The escaped name is always longer than the unescaped, so it is safe to use escaped name for the buffer length.
            int length = utf8Source.Length;
            byte[] pooledName = null;
            Span<byte> unescapedName = length <= JsonConstants.StackallocThreshold ?
                stackalloc byte[length] :
                (pooledName = ArrayPool<byte>.Shared.Rent(length));
            JsonReaderHelper.Unescape(utf8Source, unescapedName, idx, out int written);
            ReadOnlySpan<byte> propertyName = unescapedName.Slice(0, written).ToArray();
            if (pooledName != null)
            {
                // We clear the array because it is "user data" (although a property name).
                new Span<byte>(pooledName, 0, written).Clear();
                ArrayPool<byte>.Shared.Return(pooledName);
            }
            return propertyName;
        }
    }
}
namespace System
{
    public readonly struct Range : IEquatable<Range>
{
        public override string ToString()
        {
// 2 for "..", then for each index 1 for '^' and 10 for longest possible uint
            Span<char> span = stackalloc char[2 + (2 * 11)];
            int charsWritten;
            int pos = 0;
            if (Start.IsFromEnd)
            {
                span[0] = '^';
                pos = 1;
            }
            bool formatted = ((uint)Start.Value).TryFormat(span.Slice(pos), out charsWritten);
            pos += charsWritten;
            span[pos++] = '.';
            span[pos++] = '.';
            if (End.IsFromEnd)
            {
                span[pos++] = '^';
            }
            formatted = ((uint)End.Value).TryFormat(span.Slice(pos), out charsWritten);
            pos += charsWritten;
            return new string(span.Slice(0, pos));
        }
}
}
Parsing with Span
Object stack allocation
class AddOperation
{
    public int First { get; set; }
    public int Second { get; set; }
    public int Calculate()
    {
        return First + Second;
    }
}
public int Test()
{
    var operation = new AddOperation();
    operation.First = _first;
    operation.Second = _second;
    return operation.Calculate();
}
Object stack allocation disabled:
push rbx
mov rbx, rdi
movabs rdi, 0x113dc1bc0
call 0x1049f2920 (JitHelp: CORINFO_HELP_NEWSFAST)
mov edi, dword ptr [rbx + 0x8]
mov dword ptr [rax + 0x8], edi
mov edi, dword ptr [rbx + 0xc]
mov dword ptr [rax + 0xc], edi
mov edi, dword ptr [rax + 0x8]
add edi, dword ptr [rax + 0xc]
mov eax, edi
pop rbx
ret
Object stack allocation
class AddOperation
{
    public int First { get; set; }
    public int Second { get; set; }
    public int Calculate()
    {
        return First + Second;
    }
}
public int Test()
{
    var operation = new AddOperation();
    operation.First = _first;
    operation.Second = _second;
    return operation.Calculate();
}
Object stack allocation disabled:
push rbx
mov rbx, rdi
movabs rdi, 0x113dc1bc0
call 0x1049f2920 (JitHelp: CORINFO_HELP_NEWSFAST)
mov edi, dword ptr [rbx + 0x8]
mov dword ptr [rax + 0x8], edi
mov edi, dword ptr [rbx + 0xc]
mov dword ptr [rax + 0xc], edi
mov edi, dword ptr [rax + 0x8]
add edi, dword ptr [rax + 0xc]
mov eax, edi
pop rbx
ret
Object stack allocation
class AddOperation
{
    public int First { get; set; }
    public int Second { get; set; }
    public int Calculate()
    {
        return First + Second;
    }
}
public int Test()
{
    var operation = new AddOperation();
    operation.First = _first;
    operation.Second = _second;
    return operation.Calculate();
}
Object stack allocation disabled:
push rbx
mov rbx, rdi
movabs rdi, 0x113dc1bc0
call 0x1049f2920 (JitHelp: CORINFO_HELP_NEWSFAST)
mov edi, dword ptr [rbx + 0x8]
mov dword ptr [rax + 0x8], edi
mov edi, dword ptr [rbx + 0xc]
mov dword ptr [rax + 0xc], edi
mov edi, dword ptr [rax + 0x8]
add edi, dword ptr [rax + 0xc]
mov eax, edi
pop rbx
ret
Object stack allocation
class AddOperation
{
    public int First { get; set; }
    public int Second { get; set; }
    public int Calculate()
    {
        return First + Second;
    }
}
public int Test()
{
    var operation = new AddOperation();
    operation.First = _first;
    operation.Second = _second;
    return operation.Calculate();
}
Object stack allocation disabled:
push rbx
mov rbx, rdi
movabs rdi, 0x113dc1bc0
call 0x1049f2920 (JitHelp: CORINFO_HELP_NEWSFAST)
mov edi, dword ptr [rbx + 0x8]
mov dword ptr [rax + 0x8], edi
mov edi, dword ptr [rbx + 0xc]
mov dword ptr [rax + 0xc], edi
mov edi, dword ptr [rax + 0x8]
add edi, dword ptr [rax + 0xc]
mov eax, edi
pop rbx
ret
Object stack allocation
class AddOperation
{
    public int First { get; set; }
    public int Second { get; set; }
    public int Calculate()
    {
        return First + Second;
    }
}
public int Test()
{
    var operation = new AddOperation();
    operation.First = _first;
    operation.Second = _second;
    return operation.Calculate();
}
Object stack allocation disabled:
push rbx
mov rbx, rdi
movabs rdi, 0x113dc1bc0
call 0x1049f2920 (JitHelp: CORINFO_HELP_NEWSFAST)
mov edi, dword ptr [rbx + 0x8]
mov dword ptr [rax + 0x8], edi
mov edi, dword ptr [rbx + 0xc]
mov dword ptr [rax + 0xc], edi
mov edi, dword ptr [rax + 0x8]
add edi, dword ptr [rax + 0xc]
mov eax, edi
pop rbx
ret
Object stack allocation
class AddOperation
{
    public int First { get; set; }
    public int Second { get; set; }
    public int Calculate()
    {
        return First + Second;
    }
}
public int Test()
{
    var operation = new AddOperation();
    operation.First = _first;
    operation.Second = _second;
    return operation.Calculate();
}
Object stack allocation enabled:
mov eax, dword ptr [rdi + 0x8]
mov edi, dword ptr [rdi + 0xc]
add eax, edi
ret
Object stack allocation disabled:
push rbx
mov rbx, rdi
movabs rdi, 0x113dc1bc0
call 0x1049f2920 (JitHelp: CORINFO_HELP_NEWSFAST)
mov edi, dword ptr [rbx + 0x8]
mov dword ptr [rax + 0x8], edi
mov edi, dword ptr [rbx + 0xc]
mov dword ptr [rax + 0xc], edi
mov edi, dword ptr [rax + 0x8]
add edi, dword ptr [rax + 0xc]
mov eax, edi
pop rbx
ret
Stack allocations
Stack structure
Local data
Previous frame address
Return address
Arguments
Current method
stack frame
Previous
stack frame
Previous
stack frame
Previous
stack frame
Stack growth

direction
Stack structure
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Stack growth

directionrsp
Stack structure
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer Stack growth

direction
rsp
Stack structure
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer Stack growth

direction
rsp
rbp
Stack structure
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer Stack growth

direction
rsp
rdi
rbp
Stack structure
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer Stack growth

direction
rsp
rdi
rbp
Stack structure
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer Stack growth

direction
rsp
rdi
rbp
Stack structure
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer Stack growth

direction
rsp
rdi
first variable
rbp
Stack structure
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
rsp
rdi
rbp
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
rsp
rdi
rbp
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
rsp
rbp
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
rsp
rbp
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
rsp
rbp
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
first variable copy
rsp
rbp
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
second variable copy
first variable copy
rsp
rbp
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
rsp
rbp
second variable copy
first variable copy
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
TheMethod argument 2
TheMethod argument 1
rsp
rbp
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
TheMethod argument 2
TheMethod argument 1
Return address
rsp
rbp
Stack structure
second variable
int Test()
{
    var first = new YearMonth(2019, 1);
    var second = new YearMonth(2018, 10);
    return TheMethod(first, second);
}
push    rbp
sub     rsp, 0x80
lea     rbp, [rsp + 0x80]
... fill stack frame with zeroes
lea     rdi, [rbp - 0x40]
mov     esi, 0x7e3
mov     edx, 0x1
call    0x114973fe0 (YearMonth..ctor)
lea     rdi, [rbp - 0x20]
mov     esi, 0x7e2
mov     edx, 0xa
call    0x114973fe0 (YearMonth..ctor))
vmovdqu xmm0, xmmword ptr [rbp - 0x40]
vmovdqu xmmword ptr [rsp], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x30]
vmovdqu xmmword ptr [rsp + 0x10], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x20]
vmovdqu xmmword ptr [rsp + 0x20], xmm0
vmovdqu xmm0, xmmword ptr [rbp - 0x10]
vmovdqu xmmword ptr [rsp + 0x30], xmm0
call    0x114972400 (TheMethod)
lea     rsp, [rbp]
pop     rbp
ret
Previous stack frame pointer
first variable
Stack growth

direction
TheMethod argument 2
TheMethod argument 1
Return address
TheMethod local data
rbp
rsp
Minimizing structure size
in parameter modifier
namespace System
{
    public readonly struct Decimal
    {
        public static double ToDouble(decimal d)
        {
            return DecCalc.VarR8FromDec(in d);
        }
private struct DecCalc
        {
            internal static double VarR8FromDec(in decimal value)
            {
                const double ds2to64 = 1.8446744073709552e+019;
                double dbl = ((double)value.Low64 +
                    (double)value.High * ds2to64) / s_doublePowers10[value.Scale];
                if (value.IsNegative)
                    dbl = -dbl;
                return dbl;
            }
}
}
}
ref return
namespace System
{
    public static class Math
    {
        public static decimal Max(decimal val1, decimal val2)
        {
            return decimal.Max(val1, val2);
        }
}
    public readonly partial struct Decimal
    {
        internal static ref readonly decimal Max(in decimal d1, in decimal d2)
        {
            return ref DecCalc.VarDecCmp(in d1, in d2) >= 0 ? ref d1 : ref d2;
        }
}
}
Virtual calls
Virtual calls
Method table
Method 1
Method 2
Compiled method 1Compiled method 2
Object instance
Some data
More data
And even more data
Non-virtual call
lea rdi, [rbx + 0x8]
call 0x114c9f620 (MyStructure.DoAction)
public void MyMethod()
{
_someStructure.DoAction();
}
Virtual table dispatch
mov rdi, qword ptr [rdi + 0x8]
mov rax, qword ptr [rdi]
mov rax, qword ptr [rax + 0x40]
call qword ptr [rax + 0x20]
public void MyMethod()
{
    _someObject.VirtualMethod();
} Stuff
VTable indirections
Chunk 1
Header
MethodTable pointer
Instance data
Object instance
Method table
Chunk 2
…
Stuff
Target
Method 1
Method 8
Method 7
Method 6
Method 5
Method 4
Method 3
Method 2
VTable indirection
Virtual stub dispatch
public void MyMethod()
{
    _someObject.InterfaceMethod();
}
mov rdi, qword ptr [rdi + 0x8]
movabs rax, 0x107320848
call qword ptr [rax]
movabs rax, 0x10846fd08
cmp qword ptr [rdi], rax
movabs rax, 0x1083e6c60
jne 0x1073668a5
jmp rax
Lookup stub
Indirect cell
Caller
Dispatch stub Resolve stub
Target Generic resolver
Devirtualization
Verb
devirtualize
(computing, transitive) To make no longer virtual.
Devirtualization
Benchmark:
| Method | Mean | Error | StdDev |
|----------- |----------:|---------:|---------:|
| NonVirtual | 163.38 us | 1.286 us | 1.203 us |
| Virtual | 163.77 us | 1.848 us | 1.729 us |
| Interface | 191.27 us | 1.754 us | 1.641 us |
public class MyList<T> : IReadOnlyList<T>
{
    private readonly T[] _data;
    public virtual int Count => _data.Length;
    public virtual T this[int index] => _data[index];
}
public int Test()
{
var result = 0;
var data = ...
var length = data.Count;
for (var i = 0; i < length; i++)
{
    result += data[i];
}
return result;
}
Inlining
Inlining
Noun
in-line expansion (plural in-line expansions)
(software compilation)
The replacement by a compiler of a function call with a copy of
the entire function body.
Inlining
void DoStuff()
{
var user = GetUser();
Console.WriteLine(user.Name);
}
class User
{
private string _name;
public string Name
{
get => _name;
set => _name = value;
}
}
DotStuff method:
push    rbp
mov     rbp, rsp
call    0x11849bea0 (GetUser)
mov     rdi, rax
call    0x11849f650 (User.get_Name)
mov     rdi, rax
call    0x1184a0b70 (WriteLine)
pop     rbp
ret
User.get_Name method:
mov     rax, qword ptr [rdi + 0x8]
ret
Inlining
void DoStuff()
{
var user = GetUser();
Console.WriteLine(user.Name);
}
class User
{
private string _name;
public string Name
{
get => _name;
set => _name = value;
}
}
DotStuff method:
push    rbp
mov     rbp, rsp
call    0x11849bea0 (GetUser)
mov     rdi, rax
call    0x11849f650 (User.get_Name)
mov     rdi, rax
call    0x1184a0b70 (WriteLine)
pop     rbp
ret
DotStuff method (with inlining):
push    rbp
mov     rbp, rsp
call    0x12541bea0 (GetUser)
mov     rdi, qword ptr [rax + 0x8]
call    0x125420b70 (WriteLine)
pop     rbp
ret
User.get_Name method:
mov     rax, qword ptr [rdi + 0x8]
ret
void DoStuff()
{
Console.WriteLine(GetUser()._name);
}
Inlining
Benchmark:
| Method | Mean | Error | StdDev |
|----------- |----------:|---------:|---------:|
| Inlining | 58.27 us | 1.140 us | 1.120 us |
| NonVirtual | 163.38 us | 1.286 us | 1.203 us |
| Virtual | 163.77 us | 1.848 us | 1.729 us |
| Interface | 191.27 us | 1.754 us | 1.641 us |
public class MyList<T> : IReadOnlyList<T>
{
    private readonly T[] _data;
    public virtual int Count => _data.Length;
    public virtual T this[int index] => _data[index];
}
public int Test()
{
var result = 0;
var data = ...
var length = data.Count;
for (var i = 0; i < length; i++)
{
    result += data[i];
}
return result;
}
Inlining requirements
• Devirtualization / non-virtual call

• No recursion

• Heuristic:

• Inlining is profitable

• Stack size is less than 16 bytes

• IL code is smaller than 16 bytes

• …
Inlining requirements
• Devirtualization / non-virtual call

• No recursion

• Heuristic:

• Inlining is profitable

• Stack size is less than 16 bytes

• IL code is smaller than 16 bytes

• …
namespace System
{
    public static class Math
    {
        [MethodImpl(MethodImplOptions.AggressiveInlining)]
        public static decimal Min(decimal val1, decimal val2)
        {
            return decimal.Min(val1, val2);
        }
    }
}
foreach optimization
Benchmark:
| Method | Mean | Error | StdDev |
|-------- |---------:|----------:|----------:|
| List | 2.311 us | 0.0233 us | 0.0218 us |
| IList | 4.392 us | 0.0601 us | 0.0562 us |
public int Test()
{
    var result = 0;
    IList<int> data = GetData();
    foreach (var item in data)
    {
        result += item;
    }
    return result;
}
.locals init (
[0] int32,
[1] valuetype List`1/Enumerator<int32>,
)
call GetData()
callvirt instance valuetype List`1<int32>::GetEnumerator()
stloc.1
br.s loop
start: ldloca.s 1
call instance !0 valuetype List`1/Enumerator<int32>::get_Current()
ldloc.0
add
stloc.0
loop: ldloca.s 1
call instance bool valuetype List`1/Enumerator<int32>::MoveNext()
brtrue.s start
ldloc.0
ret
.locals init (
[0] int32,
[1] class IEnumerator`1<int32>,
)
call GetData()
callvirt instance class IEnumerable`1<int32>::GetEnumerator()
stloc.1
br.s loop
start: ldloc.1
callvirt instance !0 class IEnumerator::get_Current()
ldloc.0
add
stloc.0
loop: ldloc.1
callvirt instance bool IEnumerator::MoveNext()
brtrue.s start
ldloc.0
ret
namespace System.Collections.Generic
{
    public class List<T> : IList<T>, IList, IReadOnlyList<T>
    {
        public Enumerator GetEnumerator() => new Enumerator(this);
        IEnumerator<T> IEnumerable<T>.GetEnumerator() => new Enumerator(this);
        public struct Enumerator : IEnumerator<T>, IEnumerator
        {
            private readonly List<T> _list;
            private int _index;
            private T _current;
            internal Enumerator(List<T> list)
            {
                _list = list;
            }
            public bool MoveNext()
            {
                if (_index < _list._size)
                {
                    _current = _list._items[_index];
                    _index++;
                    return true;
                }
                return false;
            }
            public T Current => _current;
        }
    }
}
That’s all
Useful links
• Егор Богатов — Оптимизации внутри .NET Core

https://youtu.be/n3-j_sTtGb0

• SIMD + aligning example (corefx repo)

src/Common/src/CoreLib/System/SpanHelpers.Char.cs

• Just complex SIMD usage (corefx repo)

src/System.Memory/src/System/Buffers/Text/Base64Encoder.cs

• Book of the Runtime (a.k.a. BOTR)

https://github.com/dotnet/coreclr/tree/master/Documentation/botr
.NET LEVEL UP .NET CONFERENCE #1 IN UKRAINE KYIV 2019
@NikolayBalakin n@balakin.me

More Related Content

What's hot

Parallel K means clustering using CUDA
Parallel K means clustering using CUDAParallel K means clustering using CUDA
Parallel K means clustering using CUDAprithan
 
[241]large scale search with polysemous codes
[241]large scale search with polysemous codes[241]large scale search with polysemous codes
[241]large scale search with polysemous codesNAVER D2
 
Parallel Implementation of K Means Clustering on CUDA
Parallel Implementation of K Means Clustering on CUDAParallel Implementation of K Means Clustering on CUDA
Parallel Implementation of K Means Clustering on CUDAprithan
 
Introduction to Polyaxon
Introduction to PolyaxonIntroduction to Polyaxon
Introduction to PolyaxonYu Ishikawa
 
Where the wild things are - Benchmarking and Micro-Optimisations
Where the wild things are - Benchmarking and Micro-OptimisationsWhere the wild things are - Benchmarking and Micro-Optimisations
Where the wild things are - Benchmarking and Micro-OptimisationsMatt Warren
 
Performance and how to measure it - ProgSCon London 2016
Performance and how to measure it - ProgSCon London 2016Performance and how to measure it - ProgSCon London 2016
Performance and how to measure it - ProgSCon London 2016Matt Warren
 
Caffe framework tutorial2
Caffe framework tutorial2Caffe framework tutorial2
Caffe framework tutorial2Park Chunduck
 
Performance is a Feature! at DDD 11
Performance is a Feature! at DDD 11Performance is a Feature! at DDD 11
Performance is a Feature! at DDD 11Matt Warren
 
Lab: Foundation of Concurrent and Distributed Systems
Lab: Foundation of Concurrent and Distributed SystemsLab: Foundation of Concurrent and Distributed Systems
Lab: Foundation of Concurrent and Distributed SystemsRuochun Tzeng
 
Am I reading GC logs Correctly?
Am I reading GC logs Correctly?Am I reading GC logs Correctly?
Am I reading GC logs Correctly?Tier1 App
 
Porting and optimizing UniFrac for GPUs
Porting and optimizing UniFrac for GPUsPorting and optimizing UniFrac for GPUs
Porting and optimizing UniFrac for GPUsIgor Sfiligoi
 
Accelerating microbiome research with OpenACC
Accelerating microbiome research with OpenACCAccelerating microbiome research with OpenACC
Accelerating microbiome research with OpenACCIgor Sfiligoi
 
Gpu workshop cluster universe: scripting cuda
Gpu workshop cluster universe: scripting cudaGpu workshop cluster universe: scripting cuda
Gpu workshop cluster universe: scripting cudaFerdinand Jamitzky
 
Performance Analysis of Lattice QCD on GPUs in APGAS Programming Model
Performance Analysis of Lattice QCD on GPUs in APGAS Programming ModelPerformance Analysis of Lattice QCD on GPUs in APGAS Programming Model
Performance Analysis of Lattice QCD on GPUs in APGAS Programming ModelKoichi Shirahata
 
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDS
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDSDistributed Multi-GPU Computing with Dask, CuPy and RAPIDS
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDSPeterAndreasEntschev
 
Chainer ui v0.3 and imagereport
Chainer ui v0.3 and imagereportChainer ui v0.3 and imagereport
Chainer ui v0.3 and imagereportPreferred Networks
 
Advanced Spark and TensorFlow Meetup May 26, 2016
Advanced Spark and TensorFlow Meetup May 26, 2016Advanced Spark and TensorFlow Meetup May 26, 2016
Advanced Spark and TensorFlow Meetup May 26, 2016Chris Fregly
 

What's hot (20)

CuPy v4 and v5 roadmap
CuPy v4 and v5 roadmapCuPy v4 and v5 roadmap
CuPy v4 and v5 roadmap
 
Parallel K means clustering using CUDA
Parallel K means clustering using CUDAParallel K means clustering using CUDA
Parallel K means clustering using CUDA
 
orca_fosdem_FINAL
orca_fosdem_FINALorca_fosdem_FINAL
orca_fosdem_FINAL
 
Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to Chainer
 
[241]large scale search with polysemous codes
[241]large scale search with polysemous codes[241]large scale search with polysemous codes
[241]large scale search with polysemous codes
 
Parallel Implementation of K Means Clustering on CUDA
Parallel Implementation of K Means Clustering on CUDAParallel Implementation of K Means Clustering on CUDA
Parallel Implementation of K Means Clustering on CUDA
 
Introduction to Polyaxon
Introduction to PolyaxonIntroduction to Polyaxon
Introduction to Polyaxon
 
Where the wild things are - Benchmarking and Micro-Optimisations
Where the wild things are - Benchmarking and Micro-OptimisationsWhere the wild things are - Benchmarking and Micro-Optimisations
Where the wild things are - Benchmarking and Micro-Optimisations
 
Performance and how to measure it - ProgSCon London 2016
Performance and how to measure it - ProgSCon London 2016Performance and how to measure it - ProgSCon London 2016
Performance and how to measure it - ProgSCon London 2016
 
Caffe framework tutorial2
Caffe framework tutorial2Caffe framework tutorial2
Caffe framework tutorial2
 
Performance is a Feature! at DDD 11
Performance is a Feature! at DDD 11Performance is a Feature! at DDD 11
Performance is a Feature! at DDD 11
 
Lab: Foundation of Concurrent and Distributed Systems
Lab: Foundation of Concurrent and Distributed SystemsLab: Foundation of Concurrent and Distributed Systems
Lab: Foundation of Concurrent and Distributed Systems
 
Am I reading GC logs Correctly?
Am I reading GC logs Correctly?Am I reading GC logs Correctly?
Am I reading GC logs Correctly?
 
Porting and optimizing UniFrac for GPUs
Porting and optimizing UniFrac for GPUsPorting and optimizing UniFrac for GPUs
Porting and optimizing UniFrac for GPUs
 
Accelerating microbiome research with OpenACC
Accelerating microbiome research with OpenACCAccelerating microbiome research with OpenACC
Accelerating microbiome research with OpenACC
 
Gpu workshop cluster universe: scripting cuda
Gpu workshop cluster universe: scripting cudaGpu workshop cluster universe: scripting cuda
Gpu workshop cluster universe: scripting cuda
 
Performance Analysis of Lattice QCD on GPUs in APGAS Programming Model
Performance Analysis of Lattice QCD on GPUs in APGAS Programming ModelPerformance Analysis of Lattice QCD on GPUs in APGAS Programming Model
Performance Analysis of Lattice QCD on GPUs in APGAS Programming Model
 
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDS
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDSDistributed Multi-GPU Computing with Dask, CuPy and RAPIDS
Distributed Multi-GPU Computing with Dask, CuPy and RAPIDS
 
Chainer ui v0.3 and imagereport
Chainer ui v0.3 and imagereportChainer ui v0.3 and imagereport
Chainer ui v0.3 and imagereport
 
Advanced Spark and TensorFlow Meetup May 26, 2016
Advanced Spark and TensorFlow Meetup May 26, 2016Advanced Spark and TensorFlow Meetup May 26, 2016
Advanced Spark and TensorFlow Meetup May 26, 2016
 

Similar to .NET Fest 2019. Николай Балакин. Микрооптимизации в мире .NET

Performance Troubleshooting Using Apache Spark Metrics
Performance Troubleshooting Using Apache Spark MetricsPerformance Troubleshooting Using Apache Spark Metrics
Performance Troubleshooting Using Apache Spark MetricsDatabricks
 
Java/Scala Lab 2016. Сергей Моренец: Способы повышения эффективности в Java 8.
Java/Scala Lab 2016. Сергей Моренец: Способы повышения эффективности в Java 8.Java/Scala Lab 2016. Сергей Моренец: Способы повышения эффективности в Java 8.
Java/Scala Lab 2016. Сергей Моренец: Способы повышения эффективности в Java 8.GeeksLab Odessa
 
Apache Spark Performance Troubleshooting at Scale, Challenges, Tools, and Met...
Apache Spark Performance Troubleshooting at Scale, Challenges, Tools, and Met...Apache Spark Performance Troubleshooting at Scale, Challenges, Tools, and Met...
Apache Spark Performance Troubleshooting at Scale, Challenges, Tools, and Met...Databricks
 
Linux Systems Performance 2016
Linux Systems Performance 2016Linux Systems Performance 2016
Linux Systems Performance 2016Brendan Gregg
 
Building source code level profiler for C++.pdf
Building source code level profiler for C++.pdfBuilding source code level profiler for C++.pdf
Building source code level profiler for C++.pdfssuser28de9e
 
Computer Architecture and Organization
Computer Architecture and OrganizationComputer Architecture and Organization
Computer Architecture and Organizationssuserdfc773
 
Runtime Performance Optimizations for an OpenFOAM Simulation
Runtime Performance Optimizations for an OpenFOAM SimulationRuntime Performance Optimizations for an OpenFOAM Simulation
Runtime Performance Optimizations for an OpenFOAM SimulationFisnik Kraja
 
FMK2019 being an optimist in a pessimistic world by vincenzo menanno
FMK2019 being an optimist in a pessimistic world by vincenzo menannoFMK2019 being an optimist in a pessimistic world by vincenzo menanno
FMK2019 being an optimist in a pessimistic world by vincenzo menannoVerein FM Konferenz
 
"Ускорение сборки большого проекта на Objective-C + Swift" Иван Бондарь (Avito)
"Ускорение сборки большого проекта на Objective-C + Swift" Иван Бондарь (Avito)"Ускорение сборки большого проекта на Objective-C + Swift" Иван Бондарь (Avito)
"Ускорение сборки большого проекта на Objective-C + Swift" Иван Бондарь (Avito)AvitoTech
 
Toronto meetup 20190917
Toronto meetup 20190917Toronto meetup 20190917
Toronto meetup 20190917Bill Liu
 
Cassandra Tools and Distributed Administration (Jeffrey Berger, Knewton) | C*...
Cassandra Tools and Distributed Administration (Jeffrey Berger, Knewton) | C*...Cassandra Tools and Distributed Administration (Jeffrey Berger, Knewton) | C*...
Cassandra Tools and Distributed Administration (Jeffrey Berger, Knewton) | C*...DataStax
 
Adam Sitnik "State of the .NET Performance"
Adam Sitnik "State of the .NET Performance"Adam Sitnik "State of the .NET Performance"
Adam Sitnik "State of the .NET Performance"Yulia Tsisyk
 
State of the .Net Performance
State of the .Net PerformanceState of the .Net Performance
State of the .Net PerformanceCUSTIS
 
OSMC 2021 | pg_stat_monitor: A cool extension for better database (PostgreSQL...
OSMC 2021 | pg_stat_monitor: A cool extension for better database (PostgreSQL...OSMC 2021 | pg_stat_monitor: A cool extension for better database (PostgreSQL...
OSMC 2021 | pg_stat_monitor: A cool extension for better database (PostgreSQL...NETWAYS
 
Speed up R with parallel programming in the Cloud
Speed up R with parallel programming in the CloudSpeed up R with parallel programming in the Cloud
Speed up R with parallel programming in the CloudRevolution Analytics
 
Smart Data Conference: DL4J and DataVec
Smart Data Conference: DL4J and DataVecSmart Data Conference: DL4J and DataVec
Smart Data Conference: DL4J and DataVecJosh Patterson
 
What’s eating python performance
What’s eating python performanceWhat’s eating python performance
What’s eating python performancePiotr Przymus
 
Learning with classification and clustering, neural networks
Learning with classification and clustering, neural networksLearning with classification and clustering, neural networks
Learning with classification and clustering, neural networksShaun D'Souza
 
The CAOS framework: democratize the acceleration of compute intensive applica...
The CAOS framework: democratize the acceleration of compute intensive applica...The CAOS framework: democratize the acceleration of compute intensive applica...
The CAOS framework: democratize the acceleration of compute intensive applica...NECST Lab @ Politecnico di Milano
 

Similar to .NET Fest 2019. Николай Балакин. Микрооптимизации в мире .NET (20)

Performance Troubleshooting Using Apache Spark Metrics
Performance Troubleshooting Using Apache Spark MetricsPerformance Troubleshooting Using Apache Spark Metrics
Performance Troubleshooting Using Apache Spark Metrics
 
Java/Scala Lab 2016. Сергей Моренец: Способы повышения эффективности в Java 8.
Java/Scala Lab 2016. Сергей Моренец: Способы повышения эффективности в Java 8.Java/Scala Lab 2016. Сергей Моренец: Способы повышения эффективности в Java 8.
Java/Scala Lab 2016. Сергей Моренец: Способы повышения эффективности в Java 8.
 
Apache Spark Performance Troubleshooting at Scale, Challenges, Tools, and Met...
Apache Spark Performance Troubleshooting at Scale, Challenges, Tools, and Met...Apache Spark Performance Troubleshooting at Scale, Challenges, Tools, and Met...
Apache Spark Performance Troubleshooting at Scale, Challenges, Tools, and Met...
 
Linux Systems Performance 2016
Linux Systems Performance 2016Linux Systems Performance 2016
Linux Systems Performance 2016
 
Building source code level profiler for C++.pdf
Building source code level profiler for C++.pdfBuilding source code level profiler for C++.pdf
Building source code level profiler for C++.pdf
 
Computer Architecture and Organization
Computer Architecture and OrganizationComputer Architecture and Organization
Computer Architecture and Organization
 
BIRTE-13-Kawashima
BIRTE-13-KawashimaBIRTE-13-Kawashima
BIRTE-13-Kawashima
 
Runtime Performance Optimizations for an OpenFOAM Simulation
Runtime Performance Optimizations for an OpenFOAM SimulationRuntime Performance Optimizations for an OpenFOAM Simulation
Runtime Performance Optimizations for an OpenFOAM Simulation
 
FMK2019 being an optimist in a pessimistic world by vincenzo menanno
FMK2019 being an optimist in a pessimistic world by vincenzo menannoFMK2019 being an optimist in a pessimistic world by vincenzo menanno
FMK2019 being an optimist in a pessimistic world by vincenzo menanno
 
"Ускорение сборки большого проекта на Objective-C + Swift" Иван Бондарь (Avito)
"Ускорение сборки большого проекта на Objective-C + Swift" Иван Бондарь (Avito)"Ускорение сборки большого проекта на Objective-C + Swift" Иван Бондарь (Avito)
"Ускорение сборки большого проекта на Objective-C + Swift" Иван Бондарь (Avito)
 
Toronto meetup 20190917
Toronto meetup 20190917Toronto meetup 20190917
Toronto meetup 20190917
 
Cassandra Tools and Distributed Administration (Jeffrey Berger, Knewton) | C*...
Cassandra Tools and Distributed Administration (Jeffrey Berger, Knewton) | C*...Cassandra Tools and Distributed Administration (Jeffrey Berger, Knewton) | C*...
Cassandra Tools and Distributed Administration (Jeffrey Berger, Knewton) | C*...
 
Adam Sitnik "State of the .NET Performance"
Adam Sitnik "State of the .NET Performance"Adam Sitnik "State of the .NET Performance"
Adam Sitnik "State of the .NET Performance"
 
State of the .Net Performance
State of the .Net PerformanceState of the .Net Performance
State of the .Net Performance
 
OSMC 2021 | pg_stat_monitor: A cool extension for better database (PostgreSQL...
OSMC 2021 | pg_stat_monitor: A cool extension for better database (PostgreSQL...OSMC 2021 | pg_stat_monitor: A cool extension for better database (PostgreSQL...
OSMC 2021 | pg_stat_monitor: A cool extension for better database (PostgreSQL...
 
Speed up R with parallel programming in the Cloud
Speed up R with parallel programming in the CloudSpeed up R with parallel programming in the Cloud
Speed up R with parallel programming in the Cloud
 
Smart Data Conference: DL4J and DataVec
Smart Data Conference: DL4J and DataVecSmart Data Conference: DL4J and DataVec
Smart Data Conference: DL4J and DataVec
 
What’s eating python performance
What’s eating python performanceWhat’s eating python performance
What’s eating python performance
 
Learning with classification and clustering, neural networks
Learning with classification and clustering, neural networksLearning with classification and clustering, neural networks
Learning with classification and clustering, neural networks
 
The CAOS framework: democratize the acceleration of compute intensive applica...
The CAOS framework: democratize the acceleration of compute intensive applica...The CAOS framework: democratize the acceleration of compute intensive applica...
The CAOS framework: democratize the acceleration of compute intensive applica...
 

More from NETFest

.NET Fest 2019. Сергей Калинец. Efficient Microservice Communication with .NE...
.NET Fest 2019. Сергей Калинец. Efficient Microservice Communication with .NE....NET Fest 2019. Сергей Калинец. Efficient Microservice Communication with .NE...
.NET Fest 2019. Сергей Калинец. Efficient Microservice Communication with .NE...NETFest
 
.NET Fest 2019. Оля Гавриш. .NET Core 3.0 и будущее .NET
.NET Fest 2019. Оля Гавриш. .NET Core 3.0 и будущее .NET.NET Fest 2019. Оля Гавриш. .NET Core 3.0 и будущее .NET
.NET Fest 2019. Оля Гавриш. .NET Core 3.0 и будущее .NETNETFest
 
.NET Fest 2019. Оля Гавриш. Машинное обучение для .NET программистов
.NET Fest 2019. Оля Гавриш. Машинное обучение для .NET программистов.NET Fest 2019. Оля Гавриш. Машинное обучение для .NET программистов
.NET Fest 2019. Оля Гавриш. Машинное обучение для .NET программистовNETFest
 
.NET Fest 2019. Roberto Freato. Provisioning Azure PaaS fluently with Managem...
.NET Fest 2019. Roberto Freato. Provisioning Azure PaaS fluently with Managem....NET Fest 2019. Roberto Freato. Provisioning Azure PaaS fluently with Managem...
.NET Fest 2019. Roberto Freato. Provisioning Azure PaaS fluently with Managem...NETFest
 
.NET Fest 2019. Halil Ibrahim Kalkan. Implementing Domain Driven Design
.NET Fest 2019. Halil Ibrahim Kalkan. Implementing Domain Driven Design.NET Fest 2019. Halil Ibrahim Kalkan. Implementing Domain Driven Design
.NET Fest 2019. Halil Ibrahim Kalkan. Implementing Domain Driven DesignNETFest
 
.NET Fest 2019. Сергій Бута. Feature Toggles: Dynamic Configuration at Wirex
.NET Fest 2019. Сергій Бута. Feature Toggles: Dynamic Configuration at Wirex.NET Fest 2019. Сергій Бута. Feature Toggles: Dynamic Configuration at Wirex
.NET Fest 2019. Сергій Бута. Feature Toggles: Dynamic Configuration at WirexNETFest
 
.NET Fest 2019. Michael Staib. Hot Chocolate: GraphQL Schema Stitching with A...
.NET Fest 2019. Michael Staib. Hot Chocolate: GraphQL Schema Stitching with A....NET Fest 2019. Michael Staib. Hot Chocolate: GraphQL Schema Stitching with A...
.NET Fest 2019. Michael Staib. Hot Chocolate: GraphQL Schema Stitching with A...NETFest
 
.NET Fest 2019. Андрей Литвинов. Async lifetime tests with xUnit and AutoFixture
.NET Fest 2019. Андрей Литвинов. Async lifetime tests with xUnit and AutoFixture.NET Fest 2019. Андрей Литвинов. Async lifetime tests with xUnit and AutoFixture
.NET Fest 2019. Андрей Литвинов. Async lifetime tests with xUnit and AutoFixtureNETFest
 
.NET Fest 2019. Анатолий Колесник. Love, Death & F# Tests
.NET Fest 2019. Анатолий Колесник. Love, Death & F# Tests.NET Fest 2019. Анатолий Колесник. Love, Death & F# Tests
.NET Fest 2019. Анатолий Колесник. Love, Death & F# TestsNETFest
 
.NET Fest 2019. Алексей Голуб. Монадные парсер-комбинаторы в C# (простой спос...
.NET Fest 2019. Алексей Голуб. Монадные парсер-комбинаторы в C# (простой спос....NET Fest 2019. Алексей Голуб. Монадные парсер-комбинаторы в C# (простой спос...
.NET Fest 2019. Алексей Голуб. Монадные парсер-комбинаторы в C# (простой спос...NETFest
 
.NET Fest 2019. Roberto Freato. Azure App Service deep dive
.NET Fest 2019. Roberto Freato. Azure App Service deep dive.NET Fest 2019. Roberto Freato. Azure App Service deep dive
.NET Fest 2019. Roberto Freato. Azure App Service deep diveNETFest
 
.NET Fest 2019. Леонид Молотиевский. DotNet Core in production
.NET Fest 2019. Леонид Молотиевский. DotNet Core in production.NET Fest 2019. Леонид Молотиевский. DotNet Core in production
.NET Fest 2019. Леонид Молотиевский. DotNet Core in productionNETFest
 
.NET Fest 2019. Александр Демчук. How to measure relationships within the Com...
.NET Fest 2019. Александр Демчук. How to measure relationships within the Com....NET Fest 2019. Александр Демчук. How to measure relationships within the Com...
.NET Fest 2019. Александр Демчук. How to measure relationships within the Com...NETFest
 
.NET Fest 2019. Anna Melashkina та Philipp Bauknecht. Dragons in a Mixed Real...
.NET Fest 2019. Anna Melashkina та Philipp Bauknecht. Dragons in a Mixed Real....NET Fest 2019. Anna Melashkina та Philipp Bauknecht. Dragons in a Mixed Real...
.NET Fest 2019. Anna Melashkina та Philipp Bauknecht. Dragons in a Mixed Real...NETFest
 
.NET Fest 2019. Alex Thissen. Architecting .NET solutions in a Docker ecosystem
.NET Fest 2019. Alex Thissen. Architecting .NET solutions in a Docker ecosystem.NET Fest 2019. Alex Thissen. Architecting .NET solutions in a Docker ecosystem
.NET Fest 2019. Alex Thissen. Architecting .NET solutions in a Docker ecosystemNETFest
 
.NET Fest 2019. Stas Lebedenko. Practical serverless use cases in Azure with ...
.NET Fest 2019. Stas Lebedenko. Practical serverless use cases in Azure with ....NET Fest 2019. Stas Lebedenko. Practical serverless use cases in Azure with ...
.NET Fest 2019. Stas Lebedenko. Practical serverless use cases in Azure with ...NETFest
 
.NET Fest 2019. Сергей Медведев. How serverless makes Integration TDD a reali...
.NET Fest 2019. Сергей Медведев. How serverless makes Integration TDD a reali....NET Fest 2019. Сергей Медведев. How serverless makes Integration TDD a reali...
.NET Fest 2019. Сергей Медведев. How serverless makes Integration TDD a reali...NETFest
 
.NET Fest 2019. Сергей Корж. Natural Language Processing in .NET
.NET Fest 2019. Сергей Корж. Natural Language Processing in .NET.NET Fest 2019. Сергей Корж. Natural Language Processing in .NET
.NET Fest 2019. Сергей Корж. Natural Language Processing in .NETNETFest
 
.NET Fest 2019. Eran Stiller. Create Your Own Serverless PKI with .NET & Azur...
.NET Fest 2019. Eran Stiller. Create Your Own Serverless PKI with .NET & Azur....NET Fest 2019. Eran Stiller. Create Your Own Serverless PKI with .NET & Azur...
.NET Fest 2019. Eran Stiller. Create Your Own Serverless PKI with .NET & Azur...NETFest
 
.NET Fest 2019. Eran Stiller. 6 Lessons I Learned on My Journey from Monolith...
.NET Fest 2019. Eran Stiller. 6 Lessons I Learned on My Journey from Monolith....NET Fest 2019. Eran Stiller. 6 Lessons I Learned on My Journey from Monolith...
.NET Fest 2019. Eran Stiller. 6 Lessons I Learned on My Journey from Monolith...NETFest
 

More from NETFest (20)

.NET Fest 2019. Сергей Калинец. Efficient Microservice Communication with .NE...
.NET Fest 2019. Сергей Калинец. Efficient Microservice Communication with .NE....NET Fest 2019. Сергей Калинец. Efficient Microservice Communication with .NE...
.NET Fest 2019. Сергей Калинец. Efficient Microservice Communication with .NE...
 
.NET Fest 2019. Оля Гавриш. .NET Core 3.0 и будущее .NET
.NET Fest 2019. Оля Гавриш. .NET Core 3.0 и будущее .NET.NET Fest 2019. Оля Гавриш. .NET Core 3.0 и будущее .NET
.NET Fest 2019. Оля Гавриш. .NET Core 3.0 и будущее .NET
 
.NET Fest 2019. Оля Гавриш. Машинное обучение для .NET программистов
.NET Fest 2019. Оля Гавриш. Машинное обучение для .NET программистов.NET Fest 2019. Оля Гавриш. Машинное обучение для .NET программистов
.NET Fest 2019. Оля Гавриш. Машинное обучение для .NET программистов
 
.NET Fest 2019. Roberto Freato. Provisioning Azure PaaS fluently with Managem...
.NET Fest 2019. Roberto Freato. Provisioning Azure PaaS fluently with Managem....NET Fest 2019. Roberto Freato. Provisioning Azure PaaS fluently with Managem...
.NET Fest 2019. Roberto Freato. Provisioning Azure PaaS fluently with Managem...
 
.NET Fest 2019. Halil Ibrahim Kalkan. Implementing Domain Driven Design
.NET Fest 2019. Halil Ibrahim Kalkan. Implementing Domain Driven Design.NET Fest 2019. Halil Ibrahim Kalkan. Implementing Domain Driven Design
.NET Fest 2019. Halil Ibrahim Kalkan. Implementing Domain Driven Design
 
.NET Fest 2019. Сергій Бута. Feature Toggles: Dynamic Configuration at Wirex
.NET Fest 2019. Сергій Бута. Feature Toggles: Dynamic Configuration at Wirex.NET Fest 2019. Сергій Бута. Feature Toggles: Dynamic Configuration at Wirex
.NET Fest 2019. Сергій Бута. Feature Toggles: Dynamic Configuration at Wirex
 
.NET Fest 2019. Michael Staib. Hot Chocolate: GraphQL Schema Stitching with A...
.NET Fest 2019. Michael Staib. Hot Chocolate: GraphQL Schema Stitching with A....NET Fest 2019. Michael Staib. Hot Chocolate: GraphQL Schema Stitching with A...
.NET Fest 2019. Michael Staib. Hot Chocolate: GraphQL Schema Stitching with A...
 
.NET Fest 2019. Андрей Литвинов. Async lifetime tests with xUnit and AutoFixture
.NET Fest 2019. Андрей Литвинов. Async lifetime tests with xUnit and AutoFixture.NET Fest 2019. Андрей Литвинов. Async lifetime tests with xUnit and AutoFixture
.NET Fest 2019. Андрей Литвинов. Async lifetime tests with xUnit and AutoFixture
 
.NET Fest 2019. Анатолий Колесник. Love, Death & F# Tests
.NET Fest 2019. Анатолий Колесник. Love, Death & F# Tests.NET Fest 2019. Анатолий Колесник. Love, Death & F# Tests
.NET Fest 2019. Анатолий Колесник. Love, Death & F# Tests
 
.NET Fest 2019. Алексей Голуб. Монадные парсер-комбинаторы в C# (простой спос...
.NET Fest 2019. Алексей Голуб. Монадные парсер-комбинаторы в C# (простой спос....NET Fest 2019. Алексей Голуб. Монадные парсер-комбинаторы в C# (простой спос...
.NET Fest 2019. Алексей Голуб. Монадные парсер-комбинаторы в C# (простой спос...
 
.NET Fest 2019. Roberto Freato. Azure App Service deep dive
.NET Fest 2019. Roberto Freato. Azure App Service deep dive.NET Fest 2019. Roberto Freato. Azure App Service deep dive
.NET Fest 2019. Roberto Freato. Azure App Service deep dive
 
.NET Fest 2019. Леонид Молотиевский. DotNet Core in production
.NET Fest 2019. Леонид Молотиевский. DotNet Core in production.NET Fest 2019. Леонид Молотиевский. DotNet Core in production
.NET Fest 2019. Леонид Молотиевский. DotNet Core in production
 
.NET Fest 2019. Александр Демчук. How to measure relationships within the Com...
.NET Fest 2019. Александр Демчук. How to measure relationships within the Com....NET Fest 2019. Александр Демчук. How to measure relationships within the Com...
.NET Fest 2019. Александр Демчук. How to measure relationships within the Com...
 
.NET Fest 2019. Anna Melashkina та Philipp Bauknecht. Dragons in a Mixed Real...
.NET Fest 2019. Anna Melashkina та Philipp Bauknecht. Dragons in a Mixed Real....NET Fest 2019. Anna Melashkina та Philipp Bauknecht. Dragons in a Mixed Real...
.NET Fest 2019. Anna Melashkina та Philipp Bauknecht. Dragons in a Mixed Real...
 
.NET Fest 2019. Alex Thissen. Architecting .NET solutions in a Docker ecosystem
.NET Fest 2019. Alex Thissen. Architecting .NET solutions in a Docker ecosystem.NET Fest 2019. Alex Thissen. Architecting .NET solutions in a Docker ecosystem
.NET Fest 2019. Alex Thissen. Architecting .NET solutions in a Docker ecosystem
 
.NET Fest 2019. Stas Lebedenko. Practical serverless use cases in Azure with ...
.NET Fest 2019. Stas Lebedenko. Practical serverless use cases in Azure with ....NET Fest 2019. Stas Lebedenko. Practical serverless use cases in Azure with ...
.NET Fest 2019. Stas Lebedenko. Practical serverless use cases in Azure with ...
 
.NET Fest 2019. Сергей Медведев. How serverless makes Integration TDD a reali...
.NET Fest 2019. Сергей Медведев. How serverless makes Integration TDD a reali....NET Fest 2019. Сергей Медведев. How serverless makes Integration TDD a reali...
.NET Fest 2019. Сергей Медведев. How serverless makes Integration TDD a reali...
 
.NET Fest 2019. Сергей Корж. Natural Language Processing in .NET
.NET Fest 2019. Сергей Корж. Natural Language Processing in .NET.NET Fest 2019. Сергей Корж. Natural Language Processing in .NET
.NET Fest 2019. Сергей Корж. Natural Language Processing in .NET
 
.NET Fest 2019. Eran Stiller. Create Your Own Serverless PKI with .NET & Azur...
.NET Fest 2019. Eran Stiller. Create Your Own Serverless PKI with .NET & Azur....NET Fest 2019. Eran Stiller. Create Your Own Serverless PKI with .NET & Azur...
.NET Fest 2019. Eran Stiller. Create Your Own Serverless PKI with .NET & Azur...
 
.NET Fest 2019. Eran Stiller. 6 Lessons I Learned on My Journey from Monolith...
.NET Fest 2019. Eran Stiller. 6 Lessons I Learned on My Journey from Monolith....NET Fest 2019. Eran Stiller. 6 Lessons I Learned on My Journey from Monolith...
.NET Fest 2019. Eran Stiller. 6 Lessons I Learned on My Journey from Monolith...
 

Recently uploaded

Types of Journalistic Writing Grade 8.pptx
Types of Journalistic Writing Grade 8.pptxTypes of Journalistic Writing Grade 8.pptx
Types of Journalistic Writing Grade 8.pptxEyham Joco
 
Historical philosophical, theoretical, and legal foundations of special and i...
Historical philosophical, theoretical, and legal foundations of special and i...Historical philosophical, theoretical, and legal foundations of special and i...
Historical philosophical, theoretical, and legal foundations of special and i...jaredbarbolino94
 
भारत-रोम व्यापार.pptx, Indo-Roman Trade,
भारत-रोम व्यापार.pptx, Indo-Roman Trade,भारत-रोम व्यापार.pptx, Indo-Roman Trade,
भारत-रोम व्यापार.pptx, Indo-Roman Trade,Virag Sontakke
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentInMediaRes1
 
Meghan Sutherland In Media Res Media Component
Meghan Sutherland In Media Res Media ComponentMeghan Sutherland In Media Res Media Component
Meghan Sutherland In Media Res Media ComponentInMediaRes1
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...Marc Dusseiller Dusjagr
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptxVS Mahajan Coaching Centre
 
Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatYousafMalik24
 
Final demo Grade 9 for demo Plan dessert.pptx
Final demo Grade 9 for demo Plan dessert.pptxFinal demo Grade 9 for demo Plan dessert.pptx
Final demo Grade 9 for demo Plan dessert.pptxAvyJaneVismanos
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxpboyjonauth
 
Full Stack Web Development Course for Beginners
Full Stack Web Development Course  for BeginnersFull Stack Web Development Course  for Beginners
Full Stack Web Development Course for BeginnersSabitha Banu
 
Hierarchy of management that covers different levels of management
Hierarchy of management that covers different levels of managementHierarchy of management that covers different levels of management
Hierarchy of management that covers different levels of managementmkooblal
 
Pharmacognosy Flower 3. Compositae 2023.pdf
Pharmacognosy Flower 3. Compositae 2023.pdfPharmacognosy Flower 3. Compositae 2023.pdf
Pharmacognosy Flower 3. Compositae 2023.pdfMahmoud M. Sallam
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon AUnboundStockton
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxOH TEIK BIN
 
internship ppt on smartinternz platform as salesforce developer
internship ppt on smartinternz platform as salesforce developerinternship ppt on smartinternz platform as salesforce developer
internship ppt on smartinternz platform as salesforce developerunnathinaik
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxmanuelaromero2013
 

Recently uploaded (20)

Types of Journalistic Writing Grade 8.pptx
Types of Journalistic Writing Grade 8.pptxTypes of Journalistic Writing Grade 8.pptx
Types of Journalistic Writing Grade 8.pptx
 
Historical philosophical, theoretical, and legal foundations of special and i...
Historical philosophical, theoretical, and legal foundations of special and i...Historical philosophical, theoretical, and legal foundations of special and i...
Historical philosophical, theoretical, and legal foundations of special and i...
 
भारत-रोम व्यापार.pptx, Indo-Roman Trade,
भारत-रोम व्यापार.pptx, Indo-Roman Trade,भारत-रोम व्यापार.pptx, Indo-Roman Trade,
भारत-रोम व्यापार.pptx, Indo-Roman Trade,
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media Component
 
Meghan Sutherland In Media Res Media Component
Meghan Sutherland In Media Res Media ComponentMeghan Sutherland In Media Res Media Component
Meghan Sutherland In Media Res Media Component
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
 
Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice great
 
Final demo Grade 9 for demo Plan dessert.pptx
Final demo Grade 9 for demo Plan dessert.pptxFinal demo Grade 9 for demo Plan dessert.pptx
Final demo Grade 9 for demo Plan dessert.pptx
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptx
 
Full Stack Web Development Course for Beginners
Full Stack Web Development Course  for BeginnersFull Stack Web Development Course  for Beginners
Full Stack Web Development Course for Beginners
 
Hierarchy of management that covers different levels of management
Hierarchy of management that covers different levels of managementHierarchy of management that covers different levels of management
Hierarchy of management that covers different levels of management
 
Pharmacognosy Flower 3. Compositae 2023.pdf
Pharmacognosy Flower 3. Compositae 2023.pdfPharmacognosy Flower 3. Compositae 2023.pdf
Pharmacognosy Flower 3. Compositae 2023.pdf
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon A
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptx
 
internship ppt on smartinternz platform as salesforce developer
internship ppt on smartinternz platform as salesforce developerinternship ppt on smartinternz platform as salesforce developer
internship ppt on smartinternz platform as salesforce developer
 
ESSENTIAL of (CS/IT/IS) class 06 (database)
ESSENTIAL of (CS/IT/IS) class 06 (database)ESSENTIAL of (CS/IT/IS) class 06 (database)
ESSENTIAL of (CS/IT/IS) class 06 (database)
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptx
 

.NET Fest 2019. Николай Балакин. Микрооптимизации в мире .NET