Skip to content

Instantly share code, notes, and snippets.

View zeux's full-sized avatar

Arseny Kapoulkine zeux

2.9k followers · 0 following
View GitHub Profile
@zeux
zeux / README.md
Last active May 23, 2019 20:03
Simplifier variants
@zeux
zeux / roblox-graphics-apis-2019.md
Last active October 3, 2023 08:56

State of Roblox graphics API across all platforms, with percentage deltas since EOY 2018. Updated December 29 2019.

Windows

API Share
Direct3D 11+ 85% (+5%)
Direct3D 10.1 8.5% (-1.5%)
Direct3D 10.0 5.5% (-2.5%)
Direct3D 9 1% (-1%)
@zeux
zeux / meshoptimizer.log
Created December 5, 2018 04:43
Amazon A1 (AArch64) vs Amazon T2 (x64). VtxCodec uses SSSE3 on x64 and NEON on ARM. Look at revision history to see the diff.
a1.medium $ ./build/release/meshoptimizer buddha.obj
# buddha.obj: 549409 vertices, 1087474 triangles; read in 483.46 msec; indexed in 354.61 msec
Original : ACMR 1.556966 ATVR 3.081784 (NV 3.124747 AMD 3.277660 Intel 2.289651) Overfetch 2.105950 Overdraw 1.200370 in 0.00 msec
Random : ACMR 2.999919 ATVR 5.937897 (NV 5.937882 AMD 5.937935 Intel 5.936783) Overfetch 10.839888 Overdraw 1.218682 in 33.38 msec
Cache : ACMR 0.661465 ATVR 1.309272 (NV 1.590738 AMD 1.434356 Intel 1.138871) Overfetch 1.509062 Overdraw 1.206893 in 477.86 msec
CacheFifo: ACMR 0.689948 ATVR 1.365651 (NV 1.706663 AMD 1.516610 Intel 1.229416) Overfetch 1.552013 Overdraw 1.197034 in 146.00 msec
Overdraw : ACMR 2.776432 ATVR 5.495538 (NV 5.508446 AMD 5.527603 Intel 5.314811) Overfetch 8.624212 Overdraw 1.086317 in 209.29 msec
Fetch : ACMR 1.556966 ATVR 3.081784 (NV 3.124747 AMD 3.277660 Intel 2.289651) Overfetch 2.105950 Overdraw 1.200370 in 25.13 msec
FetchMap : ACMR 1.556966 ATVR 3.081784 (NV 3.124747 AMD 3.277660 Intel 2.289651) O
@zeux
zeux / ucd.log
Last active November 20, 2018 16:05
Loading ucd.all.grouped.xml with pugixml (https://pugixml.org), with default settings and with PUGIXML_COMPACT
~/pugixml$ cat ucd.cpp
#include "pugixml.hpp"
#include <malloc.h>
int main()
{
pugi::xml_document doc;
doc.load_file("ucd.all.grouped.xml");
malloc_stats();
}
@zeux
zeux / remap-interface-ids.cpp
Created October 2, 2018 16:49
Workaround for Adreno drivers that match varyings across stages using SPIRV names or IDs, but not locations as they should.
class RemapInterfaceIdsPass : public spvtools::opt::Pass
{
public:
const char* name() const override { return "remap-interface-ids"; }
RemapInterfaceIdsPass(uint32_t start_id): start_id(start_id)
{
}
Status Process() override
@zeux
zeux / fastformat.hpp
Created July 5, 2018 20:01
A sketch of type-safe string formatter using C++11 variadic templates and, unlike fmtlib, focusing on minimal header size & compilation time.
#pragma once
#include <string>
namespace fmt {
#define KIND(X) \
X(bool,bool) \
X(signed char,schar) \
X(unsigned char,uchar) \
@zeux
zeux / tstd.hpp
Last active September 21, 2018 14:45
A quick exercise in implementing enough parts of std::vector/any_of to reproduce MS JustMyCode example (https://blogs.msdn.microsoft.com/vcblog/2018/06/29/announcing-jmc-stepping-in-visual-studio/); tstd takes 8 F11 presses to get into the predicate body, compared to (allegedly) 140 presses for std:: implementation in VS 2017.
namespace tstd
{
template <typename T>
class vector
{
public:
typedef T* iterator;
typedef const T* const_iterator;
iterator begin() { return begin_; }
@zeux
zeux / arg-reorder.cpp
Last active June 28, 2018 02:27
An example how MSVC can change function argument evaluation order with the same compilation settings. Compile for x86 (32-bit) with MSVC 2015 or 2017 with /O2, with or without REORDER defined.
#include <stdio.h>
#include <stdint.h>
__declspec(noinline)
uint32_t giveMeRand()
{
static uint32_t result = 0xdeadbeef;
result *= 17;
return ++result;
}
@zeux
zeux / meshoptimizer-c99.diff
Created June 19, 2018 14:02
Experimental change to convert meshoptimizer code from C++03 to C99, to measure compile time & size impact of C++ on a largely-C-codebase.
diff --git a/src/indexcodec.cpp b/src/indexcodec.cpp
index 4ab92cb..18ccd43 100644
--- a/src/indexcodec.cpp
+++ b/src/indexcodec.cpp
@@ -7,9 +7,6 @@
// This work is based on:
// Fabian Giesen. Simple lossless index buffer compression & follow-up. 2013
// Conor Stokes. Vertex Cache Optimised Index Buffer Compression. 2014
-namespace meshopt
-{
@zeux
zeux / vertexcodec-comparison.txt
Last active May 23, 2019 16:45
Comparison of vertexcodec/indexcodec from meshoptimizer with Google Draco
Using fixed-point encoding for position (14 bits per component) and texture coordinates (12 bits per component), with 32-bit index buffer
and this vertex format:
// 12 bytes
struct PackedVertexOct
{
unsigned short px, py, pz;
unsigned char nu, nv; // octahedron encoded normal, aliases .pw
unsigned short tx, ty;
};