kevin/rtengine
1
0
Fork 0
Code Issues 11 Pull Requests Actions Packages Projects Releases Wiki Activity

Add early config file parsing

Browse Source 
Also cleaned up contrib/ and made lz4 and xxhash subprojects installed
via wrap.
This commit is contained in:
Kevin Trogant 2024-07-19 10:30:50 +02:00
parent 8c5b87f1de
commit 4e02d43514
27 changed files with 592 additions and 12494 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
cfg/engine_early.cfg Normal file
View File

@ -0,0 +1,11 @@
; This file contains configuration options that are used during runtime init.
rt_AssertEnabled = 1
rt_MaxConcurrentAsyncIO = 1024
rt_BufferMemoryBudget = 1073741824 ; 1GB
rt_FileTabCapacity = 1024
rt_TemporaryArenaSize = 33554432 ; 32 MB
rt_ResourceDirectory = res
rt_ResourceCacheSize = 536870912 ; 512 MB
rt_MaxCachedResources = 1024
rt_ResourceNamespaceSize = 1048576
rt_DisableResourceNamespaceLoad = 0

24
contrib/lz4/LICENSE
View File

@ -1,24 +0,0 @@
LZ4 Library
Copyright (c) 2011-2020, Yann Collet
All rights reserved.
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice, this
list of conditions and the following disclaimer in the documentation and/or
other materials provided with the distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

2766
contrib/lz4/lz4.c
View File

File diff suppressed because it is too large Load Diff

862
contrib/lz4/lz4.h
View File

@ -1,862 +0,0 @@
/*
* LZ4 - Fast LZ compression algorithm
* Header File
* Copyright (C) 2011-2020, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following disclaimer
in the documentation and/or other materials provided with the
distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at :
- LZ4 homepage : http://www.lz4.org
- LZ4 source repository : https://github.com/lz4/lz4
*/
#if defined (__cplusplus)
extern "C" {
#endif
#ifndef LZ4_H_2983827168210
#define LZ4_H_2983827168210
/* --- Dependency --- */
#include <stddef.h> /* size_t */
/**
Introduction
LZ4 is lossless compression algorithm, providing compression speed >500 MB/s per core,
scalable with multi-cores CPU. It features an extremely fast decoder, with speed in
multiple GB/s per core, typically reaching RAM speed limits on multi-core systems.
The LZ4 compression library provides in-memory compression and decompression functions.
It gives full buffer control to user.
Compression can be done in:
- a single step (described as Simple Functions)
- a single step, reusing a context (described in Advanced Functions)
- unbounded multiple steps (described as Streaming compression)
lz4.h generates and decodes LZ4-compressed blocks (doc/lz4_Block_format.md).
Decompressing such a compressed block requires additional metadata.
Exact metadata depends on exact decompression function.
For the typical case of LZ4_decompress_safe(),
metadata includes block's compressed size, and maximum bound of decompressed size.
Each application is free to encode and pass such metadata in whichever way it wants.
lz4.h only handle blocks, it can not generate Frames.
Blocks are different from Frames (doc/lz4_Frame_format.md).
Frames bundle both blocks and metadata in a specified manner.
Embedding metadata is required for compressed data to be self-contained and portable.
Frame format is delivered through a companion API, declared in lz4frame.h.
The `lz4` CLI can only manage frames.
*/
/*^***************************************************************
* Export parameters
*****************************************************************/
/*
* LZ4_DLL_EXPORT :
* Enable exporting of functions when building a Windows DLL
* LZ4LIB_VISIBILITY :
* Control library symbols visibility.
*/
#ifndef LZ4LIB_VISIBILITY
# if defined(__GNUC__) && (__GNUC__ >= 4)
# define LZ4LIB_VISIBILITY __attribute__ ((visibility ("default")))
# else
# define LZ4LIB_VISIBILITY
# endif
#endif
#if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1)
# define LZ4LIB_API __declspec(dllexport) LZ4LIB_VISIBILITY
#elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1)
# define LZ4LIB_API __declspec(dllimport) LZ4LIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
#else
# define LZ4LIB_API LZ4LIB_VISIBILITY
#endif
/*! LZ4_FREESTANDING :
* When this macro is set to 1, it enables "freestanding mode" that is
* suitable for typical freestanding environment which doesn't support
* standard C library.
*
* - LZ4_FREESTANDING is a compile-time switch.
* - It requires the following macros to be defined:
* LZ4_memcpy, LZ4_memmove, LZ4_memset.
* - It only enables LZ4/HC functions which don't use heap.
* All LZ4F_* functions are not supported.
* - See tests/freestanding.c to check its basic setup.
*/
#if defined(LZ4_FREESTANDING) && (LZ4_FREESTANDING == 1)
# define LZ4_HEAPMODE 0
# define LZ4HC_HEAPMODE 0
# define LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION 1
# if !defined(LZ4_memcpy)
# error "LZ4_FREESTANDING requires macro 'LZ4_memcpy'."
# endif
# if !defined(LZ4_memset)
# error "LZ4_FREESTANDING requires macro 'LZ4_memset'."
# endif
# if !defined(LZ4_memmove)
# error "LZ4_FREESTANDING requires macro 'LZ4_memmove'."
# endif
#elif ! defined(LZ4_FREESTANDING)
# define LZ4_FREESTANDING 0
#endif
/*------ Version ------*/
#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */
#define LZ4_VERSION_MINOR 9 /* for new (non-breaking) interface capabilities */
#define LZ4_VERSION_RELEASE 5 /* for tweaks, bug-fixes, or development */
#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
#define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE
#define LZ4_QUOTE(str) #str
#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str)
#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) /* requires v1.7.3+ */
LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version; requires v1.3.0+ */
LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; useful to check dll version; requires v1.7.5+ */
/*-************************************
* Tuning parameter
**************************************/
#define LZ4_MEMORY_USAGE_MIN 10
#define LZ4_MEMORY_USAGE_DEFAULT 14
#define LZ4_MEMORY_USAGE_MAX 20
/*!
* LZ4_MEMORY_USAGE :
* Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; )
* Increasing memory usage improves compression ratio, at the cost of speed.
* Reduced memory usage may improve speed at the cost of ratio, thanks to better cache locality.
* Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
*/
#ifndef LZ4_MEMORY_USAGE
# define LZ4_MEMORY_USAGE LZ4_MEMORY_USAGE_DEFAULT
#endif
#if (LZ4_MEMORY_USAGE < LZ4_MEMORY_USAGE_MIN)
# error "LZ4_MEMORY_USAGE is too small !"
#endif
#if (LZ4_MEMORY_USAGE > LZ4_MEMORY_USAGE_MAX)
# error "LZ4_MEMORY_USAGE is too large !"
#endif
/*-************************************
* Simple Functions
**************************************/
/*! LZ4_compress_default() :
* Compresses 'srcSize' bytes from buffer 'src'
* into already allocated 'dst' buffer of size 'dstCapacity'.
* Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize).
* It also runs faster, so it's a recommended setting.
* If the function cannot compress 'src' into a more limited 'dst' budget,
* compression stops *immediately*, and the function result is zero.
* In which case, 'dst' content is undefined (invalid).
* srcSize : max supported value is LZ4_MAX_INPUT_SIZE.
* dstCapacity : size of buffer 'dst' (which must be already allocated)
* @return : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity)
* or 0 if compression fails
* Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer).
*/
LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity);
/*! LZ4_decompress_safe() :
* @compressedSize : is the exact complete size of the compressed block.
* @dstCapacity : is the size of destination buffer (which must be already allocated),
* is an upper bound of decompressed size.
* @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity)
* If destination buffer is not large enough, decoding will stop and output an error code (negative value).
* If the source stream is detected malformed, the function will stop decoding and return a negative result.
* Note 1 : This function is protected against malicious data packets :
* it will never writes outside 'dst' buffer, nor read outside 'source' buffer,
* even if the compressed block is maliciously modified to order the decoder to do these actions.
* In such case, the decoder stops immediately, and considers the compressed block malformed.
* Note 2 : compressedSize and dstCapacity must be provided to the function, the compressed block does not contain them.
* The implementation is free to send / store / derive this information in whichever way is most beneficial.
* If there is a need for a different format which bundles together both compressed data and its metadata, consider looking at lz4frame.h instead.
*/
LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity);
/*-************************************
* Advanced Functions
**************************************/
#define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */
#define LZ4_COMPRESSBOUND(isize) ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16)
/*! LZ4_compressBound() :
Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible)
This function is primarily useful for memory allocation purposes (destination buffer size).
Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example).
Note that LZ4_compress_default() compresses faster when dstCapacity is >= LZ4_compressBound(srcSize)
inputSize : max supported value is LZ4_MAX_INPUT_SIZE
return : maximum output size in a "worst case" scenario
or 0, if input size is incorrect (too large or negative)
*/
LZ4LIB_API int LZ4_compressBound(int inputSize);
/*! LZ4_compress_fast() :
Same as LZ4_compress_default(), but allows selection of "acceleration" factor.
The larger the acceleration value, the faster the algorithm, but also the lesser the compression.
It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed.
An acceleration value of "1" is the same as regular LZ4_compress_default()
Values <= 0 will be replaced by LZ4_ACCELERATION_DEFAULT (currently == 1, see lz4.c).
Values > LZ4_ACCELERATION_MAX will be replaced by LZ4_ACCELERATION_MAX (currently == 65537, see lz4.c).
*/
LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
/*! LZ4_compress_fast_extState() :
* Same as LZ4_compress_fast(), using an externally allocated memory space for its state.
* Use LZ4_sizeofState() to know how much memory must be allocated,
* and allocate it on 8-bytes boundaries (using `malloc()` typically).
* Then, provide this buffer as `void* state` to compression function.
*/
LZ4LIB_API int LZ4_sizeofState(void);
LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
/*! LZ4_compress_destSize() :
* Reverse the logic : compresses as much data as possible from 'src' buffer
* into already allocated buffer 'dst', of size >= 'targetDestSize'.
* This function either compresses the entire 'src' content into 'dst' if it's large enough,
* or fill 'dst' buffer completely with as much data as possible from 'src'.
* note: acceleration parameter is fixed to "default".
*
* *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'.
* New value is necessarily <= input value.
* @return : Nb bytes written into 'dst' (necessarily <= targetDestSize)
* or 0 if compression fails.
*
* Note : from v1.8.2 to v1.9.1, this function had a bug (fixed in v1.9.2+):
* the produced compressed content could, in specific circumstances,
* require to be decompressed into a destination buffer larger
* by at least 1 byte than the content to decompress.
* If an application uses `LZ4_compress_destSize()`,
* it's highly recommended to update liblz4 to v1.9.2 or better.
* If this can't be done or ensured,
* the receiving decompression function should provide
* a dstCapacity which is > decompressedSize, by at least 1 byte.
* See https://github.com/lz4/lz4/issues/859 for details
*/
LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize);
/*! LZ4_decompress_safe_partial() :
* Decompress an LZ4 compressed block, of size 'srcSize' at position 'src',
* into destination buffer 'dst' of size 'dstCapacity'.
* Up to 'targetOutputSize' bytes will be decoded.
* The function stops decoding on reaching this objective.
* This can be useful to boost performance
* whenever only the beginning of a block is required.
*
* @return : the number of bytes decoded in `dst` (necessarily <= targetOutputSize)
* If source stream is detected malformed, function returns a negative result.
*
* Note 1 : @return can be < targetOutputSize, if compressed block contains less data.
*
* Note 2 : targetOutputSize must be <= dstCapacity
*
* Note 3 : this function effectively stops decoding on reaching targetOutputSize,
* so dstCapacity is kind of redundant.
* This is because in older versions of this function,
* decoding operation would still write complete sequences.
* Therefore, there was no guarantee that it would stop writing at exactly targetOutputSize,
* it could write more bytes, though only up to dstCapacity.
* Some "margin" used to be required for this operation to work properly.
* Thankfully, this is no longer necessary.
* The function nonetheless keeps the same signature, in an effort to preserve API compatibility.
*
* Note 4 : If srcSize is the exact size of the block,
* then targetOutputSize can be any value,
* including larger than the block's decompressed size.
* The function will, at most, generate block's decompressed size.
*
* Note 5 : If srcSize is _larger_ than block's compressed size,
* then targetOutputSize **MUST** be <= block's decompressed size.
* Otherwise, *silent corruption will occur*.
*/
LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity);
/*-*********************************************
* Streaming Compression Functions
***********************************************/
typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */
/**
Note about RC_INVOKED
- RC_INVOKED is predefined symbol of rc.exe (the resource compiler which is part of MSVC/Visual Studio).
https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros
- Since rc.exe is a legacy compiler, it truncates long symbol (> 30 chars)
and reports warning "RC4011: identifier truncated".
- To eliminate the warning, we surround long preprocessor symbol with
"#if !defined(RC_INVOKED) ... #endif" block that means
"skip this block when rc.exe is trying to read it".
*/
#if !defined(RC_INVOKED) /* https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros */
#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4LIB_API LZ4_stream_t* LZ4_createStream(void);
LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr);
#endif /* !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) */
#endif
/*! LZ4_resetStream_fast() : v1.9.0+
* Use this to prepare an LZ4_stream_t for a new chain of dependent blocks
* (e.g., LZ4_compress_fast_continue()).
*
* An LZ4_stream_t must be initialized once before usage.
* This is automatically done when created by LZ4_createStream().
* However, should the LZ4_stream_t be simply declared on stack (for example),
* it's necessary to initialize it first, using LZ4_initStream().
*
* After init, start any new stream with LZ4_resetStream_fast().
* A same LZ4_stream_t can be re-used multiple times consecutively
* and compress multiple streams,
* provided that it starts each new stream with LZ4_resetStream_fast().
*
* LZ4_resetStream_fast() is much faster than LZ4_initStream(),
* but is not compatible with memory regions containing garbage data.
*
* Note: it's only useful to call LZ4_resetStream_fast()
* in the context of streaming compression.
* The *extState* functions perform their own resets.
* Invoking LZ4_resetStream_fast() before is redundant, and even counterproductive.
*/
LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr);
/*! LZ4_loadDict() :
* Use this function to reference a static dictionary into LZ4_stream_t.
* The dictionary must remain available during compression.
* LZ4_loadDict() triggers a reset, so any previous data will be forgotten.
* The same dictionary will have to be loaded on decompression side for successful decoding.
* Dictionary are useful for better compression of small data (KB range).
* While LZ4 accept any input as dictionary,
* results are generally better when using Zstandard's Dictionary Builder.
* Loading a size of 0 is allowed, and is the same as reset.
* @return : loaded dictionary size, in bytes (necessarily <= 64 KB)
*/
LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize);
/*! LZ4_compress_fast_continue() :
* Compress 'src' content using data from previously compressed blocks, for better compression ratio.
* 'dst' buffer must be already allocated.
* If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster.
*
* @return : size of compressed block
* or 0 if there is an error (typically, cannot fit into 'dst').
*
* Note 1 : Each invocation to LZ4_compress_fast_continue() generates a new block.
* Each block has precise boundaries.
* Each block must be decompressed separately, calling LZ4_decompress_*() with relevant metadata.
* It's not possible to append blocks together and expect a single invocation of LZ4_decompress_*() to decompress them together.
*
* Note 2 : The previous 64KB of source data is __assumed__ to remain present, unmodified, at same address in memory !
*
* Note 3 : When input is structured as a double-buffer, each buffer can have any size, including < 64 KB.
* Make sure that buffers are separated, by at least one byte.
* This construction ensures that each block only depends on previous block.
*
* Note 4 : If input buffer is a ring-buffer, it can have any size, including < 64 KB.
*
* Note 5 : After an error, the stream status is undefined (invalid), it can only be reset or freed.
*/
LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
/*! LZ4_saveDict() :
* If last 64KB data cannot be guaranteed to remain available at its current memory location,
* save it into a safer place (char* safeBuffer).
* This is schematically equivalent to a memcpy() followed by LZ4_loadDict(),
* but is much faster, because LZ4_saveDict() doesn't need to rebuild tables.
* @return : saved dictionary size in bytes (necessarily <= maxDictSize), or 0 if error.
*/
LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxDictSize);
/*-**********************************************
* Streaming Decompression Functions
* Bufferless synchronous API
************************************************/
typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */
/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() :
* creation / destruction of streaming decompression tracking context.
* A tracking context can be re-used multiple times.
*/
#if !defined(RC_INVOKED) /* https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros */
#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void);
LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream);
#endif /* !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) */
#endif
/*! LZ4_setStreamDecode() :
* An LZ4_streamDecode_t context can be allocated once and re-used multiple times.
* Use this function to start decompression of a new stream of blocks.
* A dictionary can optionally be set. Use NULL or size 0 for a reset order.
* Dictionary is presumed stable : it must remain accessible and unmodified during next decompression.
* @return : 1 if OK, 0 if error
*/
LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize);
/*! LZ4_decoderRingBufferSize() : v1.8.2+
* Note : in a ring buffer scenario (optional),
* blocks are presumed decompressed next to each other
* up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize),
* at which stage it resumes from beginning of ring buffer.
* When setting such a ring buffer for streaming decompression,
* provides the minimum size of this ring buffer
* to be compatible with any source respecting maxBlockSize condition.
* @return : minimum ring buffer size,
* or 0 if there is an error (invalid maxBlockSize).
*/
LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize);
#define LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize) (65536 + 14 + (maxBlockSize)) /* for static allocation; maxBlockSize presumed valid */
/*! LZ4_decompress_safe_continue() :
* This decoding function allows decompression of consecutive blocks in "streaming" mode.
* The difference with the usual independent blocks is that
* new blocks are allowed to find references into former blocks.
* A block is an unsplittable entity, and must be presented entirely to the decompression function.
* LZ4_decompress_safe_continue() only accepts one block at a time.
* It's modeled after `LZ4_decompress_safe()` and behaves similarly.
*
* @LZ4_streamDecode : decompression state, tracking the position in memory of past data
* @compressedSize : exact complete size of one compressed block.
* @dstCapacity : size of destination buffer (which must be already allocated),
* must be an upper bound of decompressed size.
* @return : number of bytes decompressed into destination buffer (necessarily <= dstCapacity)
* If destination buffer is not large enough, decoding will stop and output an error code (negative value).
* If the source stream is detected malformed, the function will stop decoding and return a negative result.
*
* The last 64KB of previously decoded data *must* remain available and unmodified
* at the memory position where they were previously decoded.
* If less than 64KB of data has been decoded, all the data must be present.
*
* Special : if decompression side sets a ring buffer, it must respect one of the following conditions :
* - Decompression buffer size is _at least_ LZ4_decoderRingBufferSize(maxBlockSize).
* maxBlockSize is the maximum size of any single block. It can have any value > 16 bytes.
* In which case, encoding and decoding buffers do not need to be synchronized.
* Actually, data can be produced by any source compliant with LZ4 format specification, and respecting maxBlockSize.
* - Synchronized mode :
* Decompression buffer size is _exactly_ the same as compression buffer size,
* and follows exactly same update rule (block boundaries at same positions),
* and decoding function is provided with exact decompressed size of each block (exception for last block of the stream),
* _then_ decoding & encoding ring buffer can have any size, including small ones ( < 64 KB).
* - Decompression buffer is larger than encoding buffer, by a minimum of maxBlockSize more bytes.
* In which case, encoding and decoding buffers do not need to be synchronized,
* and encoding ring buffer can have any size, including small ones ( < 64 KB).
*
* Whenever these conditions are not possible,
* save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression,
* then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block.
*/
LZ4LIB_API int
LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode,
const char* src, char* dst,
int srcSize, int dstCapacity);
/*! LZ4_decompress_safe_usingDict() :
* Works the same as
* a combination of LZ4_setStreamDecode() followed by LZ4_decompress_safe_continue()
* However, it's stateless: it doesn't need any LZ4_streamDecode_t state.
* Dictionary is presumed stable : it must remain accessible and unmodified during decompression.
* Performance tip : Decompression speed can be substantially increased
* when dst == dictStart + dictSize.
*/
LZ4LIB_API int
LZ4_decompress_safe_usingDict(const char* src, char* dst,
int srcSize, int dstCapacity,
const char* dictStart, int dictSize);
/*! LZ4_decompress_safe_partial_usingDict() :
* Behaves the same as LZ4_decompress_safe_partial()
* with the added ability to specify a memory segment for past data.
* Performance tip : Decompression speed can be substantially increased
* when dst == dictStart + dictSize.
*/
LZ4LIB_API int
LZ4_decompress_safe_partial_usingDict(const char* src, char* dst,
int compressedSize,
int targetOutputSize, int maxOutputSize,
const char* dictStart, int dictSize);
#endif /* LZ4_H_2983827168210 */
/*^*************************************
* !!!!!! STATIC LINKING ONLY !!!!!!
***************************************/
/*-****************************************************************************
* Experimental section
*
* Symbols declared in this section must be considered unstable. Their
* signatures or semantics may change, or they may be removed altogether in the
* future. They are therefore only safe to depend on when the caller is
* statically linked against the library.
*
* To protect against unsafe usage, not only are the declarations guarded,
* the definitions are hidden by default
* when building LZ4 as a shared/dynamic library.
*
* In order to access these declarations,
* define LZ4_STATIC_LINKING_ONLY in your application
* before including LZ4's headers.
*
* In order to make their implementations accessible dynamically, you must
* define LZ4_PUBLISH_STATIC_FUNCTIONS when building the LZ4 library.
******************************************************************************/
#ifdef LZ4_STATIC_LINKING_ONLY
#ifndef LZ4_STATIC_3504398509
#define LZ4_STATIC_3504398509
#ifdef LZ4_PUBLISH_STATIC_FUNCTIONS
#define LZ4LIB_STATIC_API LZ4LIB_API
#else
#define LZ4LIB_STATIC_API
#endif
/*! LZ4_compress_fast_extState_fastReset() :
* A variant of LZ4_compress_fast_extState().
*
* Using this variant avoids an expensive initialization step.
* It is only safe to call if the state buffer is known to be correctly initialized already
* (see above comment on LZ4_resetStream_fast() for a definition of "correctly initialized").
* From a high level, the difference is that
* this function initializes the provided state with a call to something like LZ4_resetStream_fast()
* while LZ4_compress_fast_extState() starts with a call to LZ4_resetStream().
*/
LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
/*! LZ4_attach_dictionary() :
* This is an experimental API that allows
* efficient use of a static dictionary many times.
*
* Rather than re-loading the dictionary buffer into a working context before
* each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a
* working LZ4_stream_t, this function introduces a no-copy setup mechanism,
* in which the working stream references the dictionary stream in-place.
*
* Several assumptions are made about the state of the dictionary stream.
* Currently, only streams which have been prepared by LZ4_loadDict() should
* be expected to work.
*
* Alternatively, the provided dictionaryStream may be NULL,
* in which case any existing dictionary stream is unset.
*
* If a dictionary is provided, it replaces any pre-existing stream history.
* The dictionary contents are the only history that can be referenced and
* logically immediately precede the data compressed in the first subsequent
* compression call.
*
* The dictionary will only remain attached to the working stream through the
* first compression call, at the end of which it is cleared. The dictionary
* stream (and source buffer) must remain in-place / accessible / unchanged
* through the completion of the first compression call on the stream.
*/
LZ4LIB_STATIC_API void
LZ4_attach_dictionary(LZ4_stream_t* workingStream,
const LZ4_stream_t* dictionaryStream);
/*! In-place compression and decompression
*
* It's possible to have input and output sharing the same buffer,
* for highly constrained memory environments.
* In both cases, it requires input to lay at the end of the buffer,
* and decompression to start at beginning of the buffer.
* Buffer size must feature some margin, hence be larger than final size.
*
* |<------------------------buffer--------------------------------->|
* |<-----------compressed data--------->|
* |<-----------decompressed size------------------>|
* |<----margin---->|
*
* This technique is more useful for decompression,
* since decompressed size is typically larger,
* and margin is short.
*
* In-place decompression will work inside any buffer
* which size is >= LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize).
* This presumes that decompressedSize > compressedSize.
* Otherwise, it means compression actually expanded data,
* and it would be more efficient to store such data with a flag indicating it's not compressed.
* This can happen when data is not compressible (already compressed, or encrypted).
*
* For in-place compression, margin is larger, as it must be able to cope with both
* history preservation, requiring input data to remain unmodified up to LZ4_DISTANCE_MAX,
* and data expansion, which can happen when input is not compressible.
* As a consequence, buffer size requirements are much higher,
* and memory savings offered by in-place compression are more limited.
*
* There are ways to limit this cost for compression :
* - Reduce history size, by modifying LZ4_DISTANCE_MAX.
* Note that it is a compile-time constant, so all compressions will apply this limit.
* Lower values will reduce compression ratio, except when input_size < LZ4_DISTANCE_MAX,
* so it's a reasonable trick when inputs are known to be small.
* - Require the compressor to deliver a "maximum compressed size".
* This is the `dstCapacity` parameter in `LZ4_compress*()`.
* When this size is < LZ4_COMPRESSBOUND(inputSize), then compression can fail,
* in which case, the return code will be 0 (zero).
* The caller must be ready for these cases to happen,
* and typically design a backup scheme to send data uncompressed.
* The combination of both techniques can significantly reduce
* the amount of margin required for in-place compression.
*
* In-place compression can work in any buffer
* which size is >= (maxCompressedSize)
* with maxCompressedSize == LZ4_COMPRESSBOUND(srcSize) for guaranteed compression success.
* LZ4_COMPRESS_INPLACE_BUFFER_SIZE() depends on both maxCompressedSize and LZ4_DISTANCE_MAX,
* so it's possible to reduce memory requirements by playing with them.
*/
#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize) (((compressedSize) >> 8) + 32)
#define LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize) ((decompressedSize) + LZ4_DECOMPRESS_INPLACE_MARGIN(decompressedSize)) /**< note: presumes that compressedSize < decompressedSize. note2: margin is overestimated a bit, since it could use compressedSize instead */
#ifndef LZ4_DISTANCE_MAX /* history window size; can be user-defined at compile time */
# define LZ4_DISTANCE_MAX 65535 /* set to maximum value by default */
#endif
#define LZ4_COMPRESS_INPLACE_MARGIN (LZ4_DISTANCE_MAX + 32) /* LZ4_DISTANCE_MAX can be safely replaced by srcSize when it's smaller */
#define LZ4_COMPRESS_INPLACE_BUFFER_SIZE(maxCompressedSize) ((maxCompressedSize) + LZ4_COMPRESS_INPLACE_MARGIN) /**< maxCompressedSize is generally LZ4_COMPRESSBOUND(inputSize), but can be set to any lower value, with the risk that compression can fail (return code 0(zero)) */
#endif /* LZ4_STATIC_3504398509 */
#endif /* LZ4_STATIC_LINKING_ONLY */
#ifndef LZ4_H_98237428734687
#define LZ4_H_98237428734687
/*-************************************************************
* Private Definitions
**************************************************************
* Do not use these definitions directly.
* They are only exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`.
* Accessing members will expose user code to API and/or ABI break in future versions of the library.
**************************************************************/
#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2)
#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */
#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
# include <stdint.h>
typedef int8_t LZ4_i8;
typedef uint8_t LZ4_byte;
typedef uint16_t LZ4_u16;
typedef uint32_t LZ4_u32;
#else
typedef signed char LZ4_i8;
typedef unsigned char LZ4_byte;
typedef unsigned short LZ4_u16;
typedef unsigned int LZ4_u32;
#endif
/*! LZ4_stream_t :
* Never ever use below internal definitions directly !
* These definitions are not API/ABI safe, and may change in future versions.
* If you need static allocation, declare or allocate an LZ4_stream_t object.
**/
typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
struct LZ4_stream_t_internal {
LZ4_u32 hashTable[LZ4_HASH_SIZE_U32];
const LZ4_byte* dictionary;
const LZ4_stream_t_internal* dictCtx;
LZ4_u32 currentOffset;
LZ4_u32 tableType;
LZ4_u32 dictSize;
/* Implicit padding to ensure structure is aligned */
};
#define LZ4_STREAM_MINSIZE ((1UL << LZ4_MEMORY_USAGE) + 32) /* static size, for inter-version compatibility */
union LZ4_stream_u {
char minStateSize[LZ4_STREAM_MINSIZE];
LZ4_stream_t_internal internal_donotuse;
}; /* previously typedef'd to LZ4_stream_t */
/*! LZ4_initStream() : v1.9.0+
* An LZ4_stream_t structure must be initialized at least once.
* This is automatically done when invoking LZ4_createStream(),
* but it's not when the structure is simply declared on stack (for example).
*
* Use LZ4_initStream() to properly initialize a newly declared LZ4_stream_t.
* It can also initialize any arbitrary buffer of sufficient size,
* and will @return a pointer of proper type upon initialization.
*
* Note : initialization fails if size and alignment conditions are not respected.
* In which case, the function will @return NULL.
* Note2: An LZ4_stream_t structure guarantees correct alignment and size.
* Note3: Before v1.9.0, use LZ4_resetStream() instead
**/
LZ4LIB_API LZ4_stream_t* LZ4_initStream (void* buffer, size_t size);
/*! LZ4_streamDecode_t :
* Never ever use below internal definitions directly !
* These definitions are not API/ABI safe, and may change in future versions.
* If you need static allocation, declare or allocate an LZ4_streamDecode_t object.
**/
typedef struct {
const LZ4_byte* externalDict;
const LZ4_byte* prefixEnd;
size_t extDictSize;
size_t prefixSize;
} LZ4_streamDecode_t_internal;
#define LZ4_STREAMDECODE_MINSIZE 32
union LZ4_streamDecode_u {
char minStateSize[LZ4_STREAMDECODE_MINSIZE];
LZ4_streamDecode_t_internal internal_donotuse;
} ; /* previously typedef'd to LZ4_streamDecode_t */
/*-************************************
* Obsolete Functions
**************************************/
/*! Deprecation warnings
*
* Deprecated functions make the compiler generate a warning when invoked.
* This is meant to invite users to update their source code.
* Should deprecation warnings be a problem, it is generally possible to disable them,
* typically with -Wno-deprecated-declarations for gcc
* or _CRT_SECURE_NO_WARNINGS in Visual.
*
* Another method is to define LZ4_DISABLE_DEPRECATE_WARNINGS
* before including the header file.
*/
#ifdef LZ4_DISABLE_DEPRECATE_WARNINGS
# define LZ4_DEPRECATED(message) /* disable deprecation warnings */
#else
# if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */
# define LZ4_DEPRECATED(message) [[deprecated(message)]]
# elif defined(_MSC_VER)
# define LZ4_DEPRECATED(message) __declspec(deprecated(message))
# elif defined(__clang__) || (defined(__GNUC__) && (__GNUC__ * 10 + __GNUC_MINOR__ >= 45))
# define LZ4_DEPRECATED(message) __attribute__((deprecated(message)))
# elif defined(__GNUC__) && (__GNUC__ * 10 + __GNUC_MINOR__ >= 31)
# define LZ4_DEPRECATED(message) __attribute__((deprecated))
# else
# pragma message("WARNING: LZ4_DEPRECATED needs custom implementation for this compiler")
# define LZ4_DEPRECATED(message) /* disabled */
# endif
#endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */
/*! Obsolete compression functions (since v1.7.3) */
LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress (const char* src, char* dest, int srcSize);
LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* src, char* dest, int srcSize, int maxOutputSize);
LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize);
LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize);
LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
/*! Obsolete decompression functions (since v1.8.0) */
LZ4_DEPRECATED("use LZ4_decompress_fast() instead") LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize);
LZ4_DEPRECATED("use LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize);
/* Obsolete streaming functions (since v1.7.0)
* degraded functionality; do not use!
*
* In order to perform streaming compression, these functions depended on data
* that is no longer tracked in the state. They have been preserved as well as
* possible: using them will still produce a correct output. However, they don't
* actually retain any history between compression calls. The compression ratio
* achieved will therefore be no better than compressing each chunk
* independently.
*/
LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API void* LZ4_create (char* inputBuffer);
LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int LZ4_sizeofStreamState(void);
LZ4_DEPRECATED("Use LZ4_resetStream() instead") LZ4LIB_API int LZ4_resetStreamState(void* state, char* inputBuffer);
LZ4_DEPRECATED("Use LZ4_saveDict() instead") LZ4LIB_API char* LZ4_slideInputBuffer (void* state);
/*! Obsolete streaming decoding functions (since v1.7.0) */
LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize);
LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize);
/*! Obsolete LZ4_decompress_fast variants (since v1.9.0) :
* These functions used to be faster than LZ4_decompress_safe(),
* but this is no longer the case. They are now slower.
* This is because LZ4_decompress_fast() doesn't know the input size,
* and therefore must progress more cautiously into the input buffer to not read beyond the end of block.
* On top of that `LZ4_decompress_fast()` is not protected vs malformed or malicious inputs, making it a security liability.
* As a consequence, LZ4_decompress_fast() is strongly discouraged, and deprecated.
*
* The last remaining LZ4_decompress_fast() specificity is that
* it can decompress a block without knowing its compressed size.
* Such functionality can be achieved in a more secure manner
* by employing LZ4_decompress_safe_partial().
*
* Parameters:
* originalSize : is the uncompressed size to regenerate.
* `dst` must be already allocated, its size must be >= 'originalSize' bytes.
* @return : number of bytes read from source buffer (== compressed size).
* The function expects to finish at block's end exactly.
* If the source stream is detected malformed, the function stops decoding and returns a negative result.
* note : LZ4_decompress_fast*() requires originalSize. Thanks to this information, it never writes past the output buffer.
* However, since it doesn't know its 'src' size, it may read an unknown amount of input, past input buffer bounds.
* Also, since match offsets are not validated, match reads from 'src' may underflow too.
* These issues never happen if input (compressed) data is correct.
* But they may happen if input data is invalid (error or intentional tampering).
* As a consequence, use these functions in trusted environments with trusted data **only**.
*/
LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe() instead")
LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize);
LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_continue() instead")
LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize);
LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_usingDict() instead")
LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize);
/*! LZ4_resetStream() :
* An LZ4_stream_t structure must be initialized at least once.
* This is done with LZ4_initStream(), or LZ4_resetStream().
* Consider switching to LZ4_initStream(),
* invoking LZ4_resetStream() will trigger deprecation warnings in the future.
*/
LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr);
#endif /* LZ4_H_98237428734687 */
#if defined (__cplusplus)
}
#endif

19
contrib/simple_vulkan_synchronization/LICENSE.md
View File

@ -1,19 +0,0 @@
Copyright (c) 2017 Tobias Hector
Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in
the Software without restriction, including without limitation the rights to
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
of the Software, and to permit persons to whom the Software is furnished to do
so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

153
contrib/simple_vulkan_synchronization/README.md
View File

@ -1,153 +0,0 @@
# Simplified Vulkan Synchronization
In an effort to make Vulkan synchronization more accessible, I created this
stb-inspired single-header library in order to somewhat simplify the core
synchronization mechanisms in Vulkan - pipeline barriers and events.
Rather than the complex maze of enums and bitflags in Vulkan - many
combinations of which are invalid or nonsensical - this library collapses
this to a much shorter list of 40 distinct usage types, and a couple of
options for handling image layouts.
Use of other synchonization mechanisms such as semaphores, fences and render
passes are not addressed in this API at present.
## Usage
#define the symbol THSVS_SIMPLER_VULKAN_SYNCHRONIZATION_IMPLEMENTATION in
*one* C/C++ file before the #include of the header; the implementation
will be generated in that file.
## Version
alpha.9
Alpha.9 adds the thsvsGetAccessInfo function to translate access types into a thsvsVkAccessInfo.
## Version History
alpha.8
Alpha.8 adds a host preinitialization state for linear images, as well as a number of new access sets for extensions released since the last update.
alpha.7
Alpha.7 incorporates a number of fixes from @gwihlidal, and fixes
handling of pipeline stages in the presence of multiple access types or
barriers in light of other recent changes.
alpha.6
Alpha.6 fixes a typo (VK_ACCESS_TYPE_MEMORY_READ|WRITE_BIT should have been VK_ACCESS_MEMORY_READ|WRITE_BIT), and sets the pipeline stage src and dst flag bits to VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT and VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT during initialization, not 0 as per alpha.5
alpha.5
Alpha.5 now correctly zeroes out the pipeline stage flags before trying to incrementally set bits on them... common theme here, whoops.
alpha.4
Alpha.4 now correctly zeroes out the access types before trying to incrementally set bits on them (!)
alpha.3
Alpha.3 changes the following:
Uniform and vertex buffer access in one enum, matching D3D12_RESOURCE_STATE_VERTEX_AND_CONSTANT_BUFFER:
- THSVS_ACCESS_ANY_SHADER_READ_UNIFORM_BUFFER_OR_VERTEX_BUFFER
Color read *and* write access, matching D3D12_RESOURCE_STATE_RENDER_TARGET:
- THSVS_ACCESS_COLOR_ATTACHMENT_READ_WRITE
Also the "THSVS_ACCESS_\*\_SHADER_READ_SAMPLED_IMAGE" enums have been renamed to the form "THSVS_ACCESS_\*\_SHADER_READ_SAMPLED_IMAGE_OR_UNIFORM_TEXEL_BUFFER"
alpha.2
Alpha.2 adds four new resource states for "ANY SHADER ACCESS":
- THSVS_ACCESS_ANY_SHADER_READ_UNIFORM_BUFFER
- THSVS_ACCESS_ANY_SHADER_READ_SAMPLED_IMAGE
- THSVS_ACCESS_ANY_SHADER_READ_OTHER
- THSVS_ACCESS_ANY_SHADER_WRITE
alpha.1
Alpha.1 adds three new resource states:
- THSVS_ACCESS_GENERAL (Any access on the device)
- THSVS_ACCESS_DEPTH_ATTACHMENT_WRITE_STENCIL_READ_ONLY (Write access to only the depth aspect of a depth/stencil attachment)
- THSVS_ACCESS_STENCIL_ATTACHMENT_WRITE_DEPTH_READ_ONLY (Write access to only the stencil aspect of a depth/stencil attachment)
It also fixes a couple of typos, and adds clarification as to when extensions need to be enabled to use a feature.
alpha.0
This is the very first public release of this library; future revisions
of this API may change the API in an incompatible manner as feedback is
received.
Once the version becomes stable, incompatible changes will only be made
to major revisions of the API - minor revisions will only contain
bugfixes or minor additions.
## Memory Allocation
The thsvsCmdPipelineBarrier and thsvsCmdWaitEvents commands allocate
temporary storage for the Vulkan barrier equivalents in order to pass them
to the respective Vulkan commands.
These use the `THSVS_TEMP_ALLOC(size)` and `THSVS_TEMP_FREE(x)` macros,
which are by default set to alloca(size) and ((void)(x)), respectively.
If you don't want to use stack space or would rather use your own
allocation strategy, these can be overridden by defining these macros
in before #include-ing the header file with
THSVS_SIMPLER_VULKAN_SYNCHRONIZATION_IMPLEMENTATION defined.
I'd rather avoid the need for these allocations in what are likely to be
high-traffic commands, but currently just want to ship something - may
revisit this at a future date based on feedback.
## Expressiveness Compared to Raw Vulkan
Despite the fact that this API is fairly simple, it expresses 99% of
what you'd actually ever want to do in practice.
Adding the missing expressiveness would result in increased complexity
which didn't seem worth the tradeoff - however I would consider adding
something for them in future if it becomes an issue.
Here's a list of known things you can't express:
* Execution only dependencies cannot be expressed.
These are occasionally useful in conjunction with semaphores, or when
trying to be clever with scheduling - but their usage is both limited
and fairly tricky to get right anyway.
* Depth/Stencil Input Attachments can be read in a shader using either
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL or
VK_IMAGE_LAYOUT_DEPTH_STENCIL_READ_ONLY_OPTIMAL - this library
*always* uses VK_IMAGE_LAYOUT_DEPTH_STENCIL_READ_ONLY_OPTIMAL.
It's possible (though highly unlikely) when aliasing images that this
results in unnecessary transitions.
## Error Checks
By default, as with the Vulkan API, this library does NOT check for
errors.
However, a number of optional error checks (`THSVS_ERROR_CHECK_*`) can be
enabled by uncommenting the relevant #defines.
Currently, error checks simply assert at the point a failure is detected
and do not output an error message.
I certainly do not claim they capture *all* possible errors, but they
capture what should be some of the more common ones.
Use of the Vulkan Validation Layers in tandem with this library is
strongly recommended:
https://github.com/KhronosGroup/Vulkan-LoaderAndValidationLayers
## Issues
This header was clean of warnings using -Wall as of time of publishing
on both gcc 4.8.4 and clang 3.5, using the c99 standard.
There's a potential pitfall in thsvsCmdPipelineBarrier and thsvsCmdWaitEvents
where alloca is used for temporary allocations. See
[Memory Allocation](#memory-allocation) for more information.
Testing of this library is so far extremely limited with no immediate
plans to add to that - so there's bound to be some amount of bugs.
Please raise these issues on the repo issue tracker, or provide a fix
via a pull request yourself if you're so inclined.

26
contrib/simple_vulkan_synchronization/test/README.md
View File

@ -1,26 +0,0 @@
# Tests
`tests.c` defines a number of unit tests to test that various scenarios
produce the desired output.
Tests are based on the common synchronization examples on the Vulkan-Docs
wiki: https://github.com/KhronosGroup/Vulkan-Docs/wiki/Synchronization-Examples.
## Building
On a unix based system these tests can be built using:
`gcc -o tests tests.c -lvulkan`
## Running
Running is straightforward:
`./tests`
The executable will write out the tests that are run, whether they pass or
fail, and what caused them to fail if they did.
## Adding tests
If you'd like to add a test, just define a new test in main() as per those
that already exist.

357
contrib/simple_vulkan_synchronization/test/tests.c
View File

@ -1,357 +0,0 @@
// Copyright (c) 2017-2019 Tobias Hector
// Permission is hereby granted, free of charge, to any person obtaining a copy of
// this software and associated documentation files (the "Software"), to deal in
// the Software without restriction, including without limitation the rights to
// use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
// of the Software, and to permit persons to whom the Software is furnished to do
// so, subject to the following conditions:
// The above copyright notice and this permission notice shall be included in all
// copies or substantial portions of the Software.
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
// SOFTWARE.
#include <vulkan/vulkan.h>
#include <stdio.h>
#define THSVS_SIMPLER_VULKAN_SYNCHRONIZATION_IMPLEMENTATION
#include "../thsvs_simpler_vulkan_synchronization.h"
void global_barrier_test_array(const char* testName,
unsigned int numPrevAccesses,
ThsvsAccessType* prevAccesses,
unsigned int numNextAccesses,
ThsvsAccessType* nextAccesses,
VkPipelineStageFlags expectedSrcStageMask,
VkPipelineStageFlags expectedDstStageMask,
VkAccessFlags expectedSrcAccessMask,
VkAccessFlags expectedDstAccessMask)
{
ThsvsGlobalBarrier barrier = {numPrevAccesses, prevAccesses, numNextAccesses, nextAccesses};
VkMemoryBarrier vkBarrier = { 0 };
VkPipelineStageFlags srcStages = 0;
VkPipelineStageFlags dstStages = 0;
unsigned int testPassed = 1;
thsvsGetVulkanMemoryBarrier(barrier, &srcStages, &dstStages, &vkBarrier);
printf("Test: %s\n", testName);
if (srcStages != expectedSrcStageMask)
{
printf("\tUnexpected source stage %0#10X\n", srcStages);
testPassed = 0;
}
if (dstStages != expectedDstStageMask)
{
printf("\tUnexpected destination stage %0#10X\n", dstStages);
testPassed = 0;
}
if (vkBarrier.srcAccessMask != expectedSrcAccessMask)
{
printf("\tUnexpected source access mask %0#10X\n", vkBarrier.srcAccessMask);
testPassed = 0;
}
if (vkBarrier.dstAccessMask != expectedDstAccessMask)
{
printf("\tUnexpected destination access mask %0#10X\n", vkBarrier.dstAccessMask);
testPassed = 0;
}
if (testPassed == 1)
printf("\tPASSED\n");
else
printf("\tFAILED\n");
}
void global_barrier_test(const char* testName,
ThsvsAccessType prevAccess,
ThsvsAccessType nextAccess,
VkPipelineStageFlags expectedSrcStageMask,
VkPipelineStageFlags expectedDstStageMask,
VkAccessFlags expectedSrcAccessMask,
VkAccessFlags expectedDstAccessMask)
{
global_barrier_test_array(testName, 1, &prevAccess, 1, &nextAccess, expectedSrcStageMask, expectedDstStageMask, expectedSrcAccessMask, expectedDstAccessMask);
}
void image_barrier_test_array(const char* testName,
unsigned int numPrevAccesses,
ThsvsAccessType* prevAccesses,
unsigned int numNextAccesses,
ThsvsAccessType* nextAccesses,
VkPipelineStageFlags expectedSrcStageMask,
VkPipelineStageFlags expectedDstStageMask,
VkAccessFlags expectedSrcAccessMask,
VkAccessFlags expectedDstAccessMask,
VkImageLayout expectedOldLayout,
VkImageLayout expectedNewLayout)
{
ThsvsImageBarrier barrier = {numPrevAccesses, prevAccesses, numNextAccesses, nextAccesses};
VkImageMemoryBarrier vkBarrier = { 0 };
VkPipelineStageFlags srcStages = 0;
VkPipelineStageFlags dstStages = 0;
unsigned int testPassed = 1;
thsvsGetVulkanImageMemoryBarrier(barrier, &srcStages, &dstStages, &vkBarrier);
printf("Test: %s\n", testName);
if (srcStages != expectedSrcStageMask)
{
printf("\tUnexpected source stage %0#10X\n", srcStages);
testPassed = 0;
}
if (dstStages != expectedDstStageMask)
{
printf("\tUnexpected destination stage %0#10X\n", dstStages);
testPassed = 0;
}
if (vkBarrier.srcAccessMask != expectedSrcAccessMask)
{
printf("\tUnexpected source access mask %0#10X\n", vkBarrier.srcAccessMask);
testPassed = 0;
}
if (vkBarrier.dstAccessMask != expectedDstAccessMask)
{
printf("\tUnexpected destination access mask %0#10X\n", vkBarrier.dstAccessMask);
testPassed = 0;
}
if (vkBarrier.oldLayout != expectedOldLayout)
{
printf("\tUnexpected old layout %d\n", vkBarrier.oldLayout);
testPassed = 0;
}
if (vkBarrier.newLayout != expectedNewLayout)
{
printf("\tUnexpected new layout %d\n", vkBarrier.newLayout);
testPassed = 0;
}
if (testPassed == 1)
printf("\tPASSED\n");
else
printf("\tFAILED\n");
}
void image_barrier_test(const char* testName,
ThsvsAccessType prevAccess,
ThsvsAccessType nextAccess,
VkPipelineStageFlags expectedSrcStageMask,
VkPipelineStageFlags expectedDstStageMask,
VkAccessFlags expectedSrcAccessMask,
VkAccessFlags expectedDstAccessMask,
VkImageLayout expectedOldLayout,
VkImageLayout expectedNewLayout)
{
image_barrier_test_array(testName, 1, &prevAccess, 1, &nextAccess, expectedSrcStageMask, expectedDstStageMask, expectedSrcAccessMask, expectedDstAccessMask, expectedOldLayout, expectedNewLayout);
}
int main(int argc, char* argv[])
{
global_barrier_test("Compute write to storage buffer/image, Compute read from storage buffer/image",
THSVS_ACCESS_COMPUTE_SHADER_WRITE,
THSVS_ACCESS_COMPUTE_SHADER_READ_OTHER,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_ACCESS_SHADER_WRITE_BIT,
VK_ACCESS_SHADER_READ_BIT);
global_barrier_test("Compute read from storage buffer, Compute write from storage buffer",
THSVS_ACCESS_COMPUTE_SHADER_READ_OTHER,
THSVS_ACCESS_COMPUTE_SHADER_WRITE,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
0,
0);
global_barrier_test("Compute write to storage buffer, Graphics read as index buffer",
THSVS_ACCESS_COMPUTE_SHADER_WRITE,
THSVS_ACCESS_INDEX_BUFFER,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_PIPELINE_STAGE_VERTEX_INPUT_BIT,
VK_ACCESS_SHADER_WRITE_BIT,
VK_ACCESS_INDEX_READ_BIT);
{
ThsvsAccessType prevAccesses[] = {THSVS_ACCESS_COMPUTE_SHADER_WRITE};
ThsvsAccessType nextAccesses[] = {THSVS_ACCESS_INDEX_BUFFER, THSVS_ACCESS_COMPUTE_SHADER_READ_UNIFORM_BUFFER};
global_barrier_test_array("Compute write to storage buffer, Graphics read as index buffer & Compute read as uniform buffer",
1, prevAccesses,
2, nextAccesses,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_PIPELINE_STAGE_VERTEX_INPUT_BIT | VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_ACCESS_SHADER_WRITE_BIT,
VK_ACCESS_INDEX_READ_BIT | VK_ACCESS_UNIFORM_READ_BIT);
}
global_barrier_test("Compute write to storage buffer, Graphics read as indirect buffer",
THSVS_ACCESS_COMPUTE_SHADER_WRITE,
THSVS_ACCESS_INDIRECT_BUFFER,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT,
VK_ACCESS_SHADER_WRITE_BIT,
VK_ACCESS_INDIRECT_COMMAND_READ_BIT);
image_barrier_test("Compute write to storage image, Graphics fragment read as sampled image",
THSVS_ACCESS_COMPUTE_SHADER_WRITE,
THSVS_ACCESS_FRAGMENT_SHADER_READ_SAMPLED_IMAGE_OR_UNIFORM_TEXEL_BUFFER,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
VK_ACCESS_SHADER_WRITE_BIT,
VK_ACCESS_SHADER_READ_BIT,
VK_IMAGE_LAYOUT_GENERAL,
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
{
ThsvsAccessType prevAccesses[] = {THSVS_ACCESS_COMPUTE_SHADER_WRITE};
ThsvsAccessType nextAccesses[] = {THSVS_ACCESS_INDIRECT_BUFFER, THSVS_ACCESS_FRAGMENT_SHADER_READ_UNIFORM_BUFFER};
global_barrier_test_array("Compute write to storage texel buffer, Graphics read as indirect buffer & fragment read as uniform buffer",
1, prevAccesses,
2, nextAccesses,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT | VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
VK_ACCESS_SHADER_WRITE_BIT,
VK_ACCESS_INDIRECT_COMMAND_READ_BIT | VK_ACCESS_UNIFORM_READ_BIT);
}
image_barrier_test("Graphics write to color attachment, Compute read from sampled image",
THSVS_ACCESS_COLOR_ATTACHMENT_WRITE,
THSVS_ACCESS_COMPUTE_SHADER_READ_SAMPLED_IMAGE_OR_UNIFORM_TEXEL_BUFFER,
VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
VK_ACCESS_SHADER_READ_BIT,
VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL,
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
image_barrier_test("Graphics write to depth attachment, Compute read from sampled image",
THSVS_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE,
THSVS_ACCESS_COMPUTE_SHADER_READ_SAMPLED_IMAGE_OR_UNIFORM_TEXEL_BUFFER,
VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT | VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT,
VK_ACCESS_SHADER_READ_BIT,
VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL,
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
image_barrier_test("Graphics write to depth attachment, Graphics fragment read from input attachment",
THSVS_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE,
THSVS_ACCESS_FRAGMENT_SHADER_READ_DEPTH_STENCIL_INPUT_ATTACHMENT,
VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT | VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT,
VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT,
VK_ACCESS_INPUT_ATTACHMENT_READ_BIT,
VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL,
VK_IMAGE_LAYOUT_DEPTH_STENCIL_READ_ONLY_OPTIMAL);
image_barrier_test("Graphics write to depth attachment, Graphics fragment read from sampled image",
THSVS_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE,
THSVS_ACCESS_FRAGMENT_SHADER_READ_SAMPLED_IMAGE_OR_UNIFORM_TEXEL_BUFFER,
VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT | VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT,
VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT,
VK_ACCESS_SHADER_READ_BIT,
VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL,
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
image_barrier_test("Graphics write to color attachment, Graphics fragment read from input attachment",
THSVS_ACCESS_COLOR_ATTACHMENT_WRITE,
THSVS_ACCESS_FRAGMENT_SHADER_READ_COLOR_INPUT_ATTACHMENT,
VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
VK_ACCESS_INPUT_ATTACHMENT_READ_BIT,
VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL,
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
image_barrier_test("Graphics write to color attachment, Graphics fragment read from sampled image",
THSVS_ACCESS_COLOR_ATTACHMENT_WRITE,
THSVS_ACCESS_FRAGMENT_SHADER_READ_SAMPLED_IMAGE_OR_UNIFORM_TEXEL_BUFFER,
VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
VK_ACCESS_SHADER_READ_BIT,
VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL,
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
image_barrier_test("Graphics write to color attachment, Graphics vertex read from sampled image",
THSVS_ACCESS_COLOR_ATTACHMENT_WRITE,
THSVS_ACCESS_VERTEX_SHADER_READ_SAMPLED_IMAGE_OR_UNIFORM_TEXEL_BUFFER,
VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
VK_PIPELINE_STAGE_VERTEX_SHADER_BIT,
VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
VK_ACCESS_SHADER_READ_BIT,
VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL,
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
image_barrier_test("Graphics fragment read from sampled image, Graphics write to color attachment",
THSVS_ACCESS_FRAGMENT_SHADER_READ_SAMPLED_IMAGE_OR_UNIFORM_TEXEL_BUFFER,
THSVS_ACCESS_COLOR_ATTACHMENT_WRITE,
VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
0,
0,
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL,
VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL);
global_barrier_test("None, Transfer read from buffer",
THSVS_ACCESS_NONE,
THSVS_ACCESS_TRANSFER_READ,
VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
VK_PIPELINE_STAGE_TRANSFER_BIT,
0,
0);
global_barrier_test("Transfer write to buffer, Graphics read from vertex buffer",
THSVS_ACCESS_TRANSFER_WRITE,
THSVS_ACCESS_VERTEX_BUFFER,
VK_PIPELINE_STAGE_TRANSFER_BIT,
VK_PIPELINE_STAGE_VERTEX_INPUT_BIT,
VK_ACCESS_TRANSFER_WRITE_BIT,
VK_ACCESS_VERTEX_ATTRIBUTE_READ_BIT);
image_barrier_test("Transfer write to image, Graphics fragment read from sampled image",
THSVS_ACCESS_TRANSFER_WRITE,
THSVS_ACCESS_FRAGMENT_SHADER_READ_SAMPLED_IMAGE_OR_UNIFORM_TEXEL_BUFFER,
VK_PIPELINE_STAGE_TRANSFER_BIT,
VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
VK_ACCESS_TRANSFER_WRITE_BIT,
VK_ACCESS_SHADER_READ_BIT,
VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL,
VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
image_barrier_test("Graphics color attachment write, Presentation",
THSVS_ACCESS_COLOR_ATTACHMENT_WRITE,
THSVS_ACCESS_PRESENT,
VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT,
VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
0,
VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL,
VK_IMAGE_LAYOUT_PRESENT_SRC_KHR);
global_barrier_test("Full pipeline barrier",
THSVS_ACCESS_GENERAL,
THSVS_ACCESS_GENERAL,
VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT,
VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT);
}

1397
contrib/simple_vulkan_synchronization/thsvs_simpler_vulkan_synchronization.h
View File

File diff suppressed because it is too large Load Diff

26
contrib/xxhash/LICENSE
View File

@ -1,26 +0,0 @@
xxHash Library
Copyright (c) 2012-2021 Yann Collet
All rights reserved.
BSD 2-Clause License (https://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice, this
list of conditions and the following disclaimer in the documentation and/or
other materials provided with the distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

43
contrib/xxhash/xxhash.c
View File

@ -1,43 +0,0 @@
/*
* xxHash - Extremely Fast Hash algorithm
* Copyright (C) 2012-2021 Yann Collet
*
* BSD 2-Clause License (https://www.opensource.org/licenses/bsd-license.php)
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met:
*
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following disclaimer
* in the documentation and/or other materials provided with the
* distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* You can contact the author at:
* - xxHash homepage: https://www.xxhash.com
* - xxHash source repository: https://github.com/Cyan4973/xxHash
*/
/*
* xxhash.c instantiates functions defined in xxhash.h
*/
#define XXH_STATIC_LINKING_ONLY /* access advanced declarations */
#define XXH_IMPLEMENTATION /* access definitions */
#include "xxhash.h"

6773
contrib/xxhash/xxhash.h
View File

File diff suppressed because it is too large Load Diff

2
meson.build
View File

@ -1,6 +1,6 @@
project('rtengine', ['c', 'cpp'],
default_options: ['buildtype=debug',
'b_sanitize=address',
'b_sanitize=none',
'c_std=c17',
'cpp_std=c++20',
'warning_level=3',

2
src/runtime/compression.c
View File

@ -1,6 +1,6 @@
#include "compression.h"
#include <lz4/lz4.h>
#include <lz4.h>
RT_DLLEXPORT size_t rtGetCompressionBound(size_t uncompressed_size) {
return (size_t)LZ4_compressBound((int)uncompressed_size);

291
src/runtime/config.c
View File

@ -1,41 +1,304 @@
#include "config.h"
#include "fsutils.h"
#include "runtime.h"
#include "threading.h"
#include "aio.h"
#include "buffer_manager.h"
#include "file_tab.h"
#include "mem_arena.h"
#include "string_storage.h"
#include <ini.h>
#include <stddef.h>
#include <stdlib.h>
#include <string.h>
#define RT_MAX_CVARS 1024
#define RT_MAX_CVARS 1024
#define RT_MAX_EVENT_HANDLERS 1024
static rt_cvar *_vars[RT_MAX_CVARS];
static unsigned int _next = 0;
static rt_mutex *_mutex = NULL;
typedef struct rt_cvar_change_event_list {
rt_cvar_change_event_handler_fn *Handler;
void *userdata;
struct rt_cvar_change_event_list *next;
} rt_cvar_change_event_list;
void rtRegisterCVAR(rt_cvar *cvar) {
/* TODO(Kevin): Check if we have a loaded value for that cvar.
* If yes, override the provided default value. */
typedef struct {
rt_cvar *cvar;
rt_cvar_change_event_list *change_event_handlers;
} rt_cvar_container;
static rt_cvar_container _vars[RT_MAX_CVARS];
static unsigned int _next_cvar = 0;
static rt_cvar_change_event_list _change_event_handlers[RT_MAX_EVENT_HANDLERS];
static unsigned int _next_event_handler = 0;
static rt_mutex *_mutex = NULL;
RT_DLLEXPORT void rtRegisterCVAR(rt_cvar *cvar) {
if (!_mutex)
_mutex = rtCreateMutex();
rtLockMutex(_mutex);
if (_next < RT_MAX_CVARS) {
_vars[_next++] = cvar;
if (_next_cvar < RT_MAX_CVARS) {
rtLog("CVAR", "Registered cvar %s", cvar->name);
_vars[_next_cvar].cvar = cvar;
_vars[_next_cvar].change_event_handlers = NULL;
++_next_cvar;
} else {
rtReportError("cvar", "Ran out of space for CVars");
rtReportError("CVAR", "Ran out of space for CVars");
}
rtUnlockMutex(_mutex);
}
rt_cvar *rtGetCVAR(const char *name) {
RT_DLLEXPORT rt_cvar *rtGetCVAR(const char *name) {
if (!_mutex)
_mutex = rtCreateMutex();
rt_cvar *var = NULL;
rtLockMutex(_mutex);
for (unsigned int i = 0; i < _next; ++i) {
if (strcmp(name, _vars[i]->name) == 0) {
var = _vars[i];
for (unsigned int i = 0; i < _next_cvar; ++i) {
if (strcmp(name, _vars[i].cvar->name) == 0) {
var = _vars[i].cvar;
break;
}
}
rtUnlockMutex(_mutex);
return var;
}
RT_DLLEXPORT void rtRegisterCVARChangeEventHandler(rt_cvar *cvar,
rt_cvar_change_event_handler_fn *event_handler,
void *userdata) {
RT_VERIFY(_mutex);
rtLockMutex(_mutex);
if (_next_event_handler == RT_MAX_EVENT_HANDLERS) {
rtReportError("CVAR", "Ran out of space for CVar change event handlers");
rtUnlockMutex(_mutex);
return;
}
for (unsigned int i = 0; i < _next_cvar; ++i) {
if (_vars[i].cvar == cvar) {
rt_cvar_change_event_list *entry = &_change_event_handlers[_next_event_handler++];
entry->Handler = event_handler;
entry->next = _vars[i].change_event_handlers;
entry->userdata = userdata;
_vars[i].change_event_handlers = entry;
}
}
rtUnlockMutex(_mutex);
}
RT_DLLEXPORT void rtNotifyCVARChange(const rt_cvar *cvar) {
#ifndef RT_DONT_LOG_CVAR_CHANGES
switch (cvar->type) {
case RT_CVAR_TYPE_INT:
rtLog("CVAR", "Changed %s to %d.", cvar->name, cvar->i);
break;
case RT_CVAR_TYPE_FLOAT:
rtLog("CVAR", "Changed %s to %f.", cvar->name, cvar->f);
break;
case RT_CVAR_TYPE_STRING:
rtLog("CVAR", "Changed %s to '%s'.", cvar->name, cvar->s);
break;
case RT_CVAR_TYPE_SIZE:
rtLog("CVAR", "Changed %s to %zu.", cvar->name, cvar->sz);
break;
default:
rtLog("CVAR", "Changed %s, but the cvar has an invalid type.", cvar->name);
break;
}
#endif
RT_VERIFY(_mutex);
rtLockMutex(_mutex);
for (unsigned int i = 0; i < _next_cvar; ++i) {
if (_vars[i].cvar == cvar) {
rt_cvar_change_event_list *entry = _vars[i].change_event_handlers;
rtUnlockMutex(_mutex);
while (entry) {
/* We don't want to hold the mutex while the event handler runs,
* because that would prevent any calls to CVar functions. */
entry->Handler(_vars[i].cvar, entry->userdata);
rtLockMutex(_mutex);
entry = entry->next;
rtUnlockMutex(_mutex);
}
return;
}
}
/* Not found... */
rtUnlockMutex(_mutex);
}
static int Handler(void *user, const char *section, const char *name, const char *value) {
/* We currently ignore sections. They could be used to categorize variables by system? */
RT_UNUSED(section);
const char *file_path = user;
rt_cvar *cvar = rtGetCVAR(name);
if (!cvar) {
/* Not a critical error. */
rtLog("CVAR", "Unknown CVar %s in config file %s.", name, file_path);
return 1;
}
int num_read = 0;
switch (cvar->type) {
case RT_CVAR_TYPE_INT:
num_read = sscanf(value, "%d", &cvar->i);
break;
case RT_CVAR_TYPE_FLOAT:
num_read = sscanf(value, "%f", &cvar->f);
break;
case RT_CVAR_TYPE_STRING: {
num_read = 1;
char *copy = rtStoreString(value);
if (!copy) {
rtReportError("CVAR",
"Failed to store string value of cvar %s in config file %s.",
name,
file_path);
return 0;
}
cvar->s = copy;
break;
}
case RT_CVAR_TYPE_SIZE:
num_read = sscanf(value, "%zu", &cvar->sz);
break;
default:
rtReportError("CVAR", "CVar %s has an invalid type.", cvar->name);
return 0;
}
if (num_read == 1) {
rtNotifyCVARChange(cvar);
} else {
rtLog("CVAR", "Failed to read value of CVar %s in config file %s.", cvar->name, file_path);
}
return 1;
}
/* Config files are ini files */
static rt_result ProcessConfigFile(const void *buffer, size_t fsz, const char *file_path) {
rt_result result = RT_SUCCESS;
if (ini_parse_string(buffer, Handler, (void *)file_path) < 0) {
rtLog("CVAR", "Failed to parse config file '%s'.", file_path);
return RT_UNKNOWN_ERROR;
}
return result;
}
RT_DLLEXPORT rt_result rtProcessConfigFiles(unsigned int count, const rt_file_id *fids) {
if (count > RT_LOAD_BATCH_MAX_SIZE) {
rtReportError("CVAR",
"Got %u config files, but the maximum number of config files is %u.",
count,
RT_LOAD_BATCH_MAX_SIZE);
return RT_INVALID_VALUE;
}
typedef struct {
void *buffer;
size_t fsz;
const char *path;
} config_file_buf;
rt_temp_arena temp = rtGetTemporaryArena(NULL, 0);
if (!temp.arena)
return RT_OUT_OF_MEMORY;
config_file_buf *configs = RT_ARENA_PUSH_ARRAY_ZERO(temp.arena, config_file_buf, count);
if (!configs) {
rtReturnTemporaryArena(temp);
return RT_OUT_OF_MEMORY;
}
rt_aio_handle *aios = RT_ARENA_PUSH_ARRAY_ZERO(temp.arena, rt_aio_handle, count);
if (!configs) {
rtReturnTemporaryArena(temp);
return RT_OUT_OF_MEMORY;
}
rt_result res = RT_SUCCESS;
rt_load_batch load_batch;
load_batch.num_loads = count;
for (unsigned int i = 0; i < count; ++i) {
const char *path = rtGetFilePath(fids[i]);
if (!path) {
rtReportError("CVAR", "Invalid config file path!");
res = RT_INVALID_VALUE;
goto out;
}
size_t fsz = rtGetFileSize(path);
load_batch.loads[i].dest = rtAllocBuffer(fsz);
if (!load_batch.loads[i].dest) {
rtReportError("CVAR", "Failed to allocate memory for config file.");
res = RT_OUT_OF_MEMORY;
goto out;
}
load_batch.loads[i].num_bytes = fsz;
load_batch.loads[i].offset = 0;
load_batch.loads[i].file = fids[i];
configs[i].buffer = load_batch.loads[i].dest;
configs[i].fsz = fsz;
configs[i].path = path;
}
if ((res = rtSubmitLoadBatch(&load_batch, aios)) != RT_SUCCESS) {
goto out;
}
for (unsigned int i = 0; i < count; ++i) {
rt_aio_state state = rtWaitForAIOCompletion(aios[i]);
if (state == RT_AIO_STATE_FINISHED) {
res = ProcessConfigFile(configs[i].buffer, configs[i].fsz, configs[i].path);
if (res != RT_SUCCESS)
goto out;
} else {
RT_ASSERT(state == RT_AIO_STATE_FAILED, "Unexpected aio state.");
res = RT_UNKNOWN_ERROR;
goto out;
}
}
out:
for (unsigned int i = 0; i < count; ++i) {
if (configs[i].buffer)
rtReleaseBuffer(configs[i].buffer, configs[i].fsz);
if (aios[i] != RT_AIO_INVALID_HANDLE)
rtReleaseAIO(aios[i]);
}
rtReturnTemporaryArena(temp);
return res;
}
/* This gets called before _any_ engine systems are available (especially AIO, ftab and
* Buffermanager) */
void ProcessEarlyEngineConfigs(void) {
const char *engine_cfgs[] = {"cfg/engine_early.cfg"};
void *buf = NULL;
size_t buf_sz = 0;
for (unsigned int i = 0; i < RT_ARRAY_COUNT(engine_cfgs); ++i) {
if (!rtDoesFileExist(engine_cfgs[i])) {
rtLog("CVAR", "Could not find early engine config file %s", engine_cfgs[i]);
continue;
}
size_t fsz = rtGetFileSize(engine_cfgs[i]);
if ((fsz + 1) > buf_sz) {
buf = realloc(buf, fsz + 1);
buf_sz = fsz + 1;
}
if (!rtSyncReadWholeFile(engine_cfgs[i], buf, buf_sz)) {
rtLog("CVAR", "Failed to read early engine config file %s", engine_cfgs[i]);
continue;
}
((char *)buf)[fsz] = '\0';
if (ProcessConfigFile(buf, fsz, engine_cfgs[i]) != RT_SUCCESS) {
rtLog("CVAR", "Failed to process early engine config file %s", engine_cfgs[i]);
}
}
free(buf);
}

17
src/runtime/config.h
View File

@ -1,6 +1,7 @@
#ifndef RT_CONFIG_H
#define RT_CONFIG_H
#include "file_tab.h"
#include "runtime.h"
#ifdef __cplusplus
@ -26,6 +27,8 @@ typedef struct {
rt_cvar_type type;
} rt_cvar;
typedef void(rt_cvar_change_event_handler_fn)(rt_cvar *cvar, void *userdata);
/* n variable name, d description string, v default value*/
#define RT_CVAR_I(n, d, v) \
rt_cvar n = {.name = #n, .description = d, .i = (v), .type = RT_CVAR_TYPE_INT}
@ -40,6 +43,20 @@ RT_DLLEXPORT void rtRegisterCVAR(rt_cvar *cvar);
RT_DLLEXPORT rt_cvar *rtGetCVAR(const char *name);
/* Change event handlers are called when rtNotifyCVARChange is called.
* The system gives no guarantees about the order in which these are called.
*
* NOTE: A internal mutex is held while the event handlers run, which means that */
RT_DLLEXPORT void rtRegisterCVARChangeEventHandler(rt_cvar *cvar,
rt_cvar_change_event_handler_fn *event_handler,
void *userdata);
RT_DLLEXPORT void rtNotifyCVARChange(const rt_cvar *cvar);
/* Load and parse configuration files.
* They are processed in-order, meaning later files can overwrite earlier files. */
RT_DLLEXPORT rt_result rtProcessConfigFiles(unsigned int count, const rt_file_id *fids);
#ifdef __cplusplus
}
#endif

60
src/runtime/fsutils.c
View File

@ -98,7 +98,14 @@ RT_DLLEXPORT size_t rtGetFileSize(const char *path) {
return (size_t)attribs.nFileSizeHigh << 32 | (size_t)attribs.nFileSizeLow;
}
uint64_t rtGetCurrentTimestamp(void) {
RT_DLLEXPORT bool rtDoesFileExist(const char *path) {
WCHAR wpath[MAX_PATH];
MultiByteToWideChar(CP_UTF8, MB_PRECOMPOSED, path, -1, wpath, MAX_PATH);
DWORD dwAttrib = GetFileAttributesW(wpath);
return (dwAttrib != INVALID_FILE_ATTRIBUTES && !(dwAttrib & FILE_ATTRIBUTE_DIRECTORY));
}
RT_DLLEXPORT uint64_t rtGetCurrentTimestamp(void) {
FILETIME ft;
GetSystemTimeAsFileTime(&ft);
uint64_t ts = ft.dwLowDateTime;
@ -106,7 +113,7 @@ uint64_t rtGetCurrentTimestamp(void) {
return ts;
}
uint64_t rtGetFileModificationTimestamp(const char *path) {
RT_DLLEXPORT uint64_t rtGetFileModificationTimestamp(const char *path) {
WCHAR wpath[MAX_PATH];
MultiByteToWideChar(CP_UTF8, MB_PRECOMPOSED, path, -1, wpath, MAX_PATH);
WIN32_FILE_ATTRIBUTE_DATA attribs;
@ -117,12 +124,34 @@ uint64_t rtGetFileModificationTimestamp(const char *path) {
return ts;
}
RT_DLLEXPORT bool rtSyncReadWholeFile(const char *path, void *dest, size_t dest_size) {
size_t fsz = rtGetFileSize(path);
if (fsz > dest_size)
return false;
WCHAR wpath[MAX_PATH];
MultiByteToWideChar(CP_UTF8, MB_PRECOMPOSED, path, -1, wpath, MAX_PATH);
HANDLE hFile = CreateFileW(wpath,
GENERIC_READ,
FILE_SHARE_READ,
NULL,
OPEN_EXISTING,
FILE_ATTRIBUTE_NORMAL,
NULL);
if (!hFile)
return false;
BOOL bResult = ReadFile(hFile, dest, (DWORD)fsz, NULL, NULL);
CloseHandle(hFile);
return (bool)bResult;
}
#elif defined(__linux__)
#include <string.h>
#include <sys/dir.h>
#include <sys/stat.h>
#include <time.h>
#include <stdio.h>
struct rt_scandir_handle_s {
DIR *handle;
@ -208,17 +237,40 @@ RT_DLLEXPORT size_t rtGetFileSize(const char *path) {
return (size_t)st.st_size;
}
uint64_t rtGetCurrentTimestamp(void) {
RT_DLLEXPORT bool rtDoesFileExist(const char *path) {
struct stat st;
if (stat(path, &st) != 0)
return 0;
return 1;
}
RT_DLLEXPORT uint64_t rtGetCurrentTimestamp(void) {
struct timespec ts;
clock_gettime(CLOCK_REALTIME, &ts);
return (uint64_t)ts.tv_sec;
}
uint64_t rtGetFileModificationTimestamp(const char *path) {
RT_DLLEXPORT uint64_t rtGetFileModificationTimestamp(const char *path) {
struct stat st;
if (stat(path, &st) != 0)
return 0;
return (uint64_t)st.st_mtim.tv_sec;
}
RT_DLLEXPORT bool rtSyncReadWholeFile(const char *path, void *dest, size_t dest_size) {
FILE *f = fopen(path, "rb");
if (!f)
return false;
fseek(f, SEEK_END, 0);
size_t fsz = (size_t)ftell(f);
fseek(f, SEEK_SET, 0);
if (fsz > dest_size) {
fclose(f);
return false;
}
size_t n = fread(dest, 1 fsz, f);
fclose(f);
return n == fsz;
}
#endif

6
src/runtime/fsutils.h
View File

@ -35,9 +35,15 @@ RT_DLLEXPORT size_t rtGetFileSize(const char *path);
RT_DLLEXPORT uint64_t rtGetFileModificationTimestamp(const char *path);
RT_DLLEXPORT bool rtDoesFileExist(const char *path);
/* Does not really fit here, but it is mostly useful for comparison with file timestamps. */
RT_DLLEXPORT uint64_t rtGetCurrentTimestamp(void);
/* CAUTION: This does a synchronous file read!!! ONLY use this IF YOU KNOW WHAT YOU ARE DOING.
* 99.9% of file reads should probably use the AIO system instead. */
RT_DLLEXPORT bool rtSyncReadWholeFile(const char *path, void *dest, size_t dest_size);
#ifdef __cplusplus
}
#endif

7
src/runtime/hashing.c
View File

@ -1,17 +1,18 @@
#include "hashing.h"
#include <xxhash/xxhash.h>
#include <xxhash.h>
#include <assert.h>
/* XXH32 of "recreational.tech" */
/* XXH32/64 of "recreational.tech" with seed 0 */
#define HASH32_SEED 0xd9035e35
#define HASH64_SEED 0xa14e16c3ae8b282dULL
static_assert(sizeof(rt_hash64) == sizeof(XXH64_hash_t), "Size mismatch between rt_hash64 and XXH64_hash_t!");
static_assert(sizeof(rt_hash32) == sizeof(XXH32_hash_t),
"Size mismatch between rt_hash32 and XXH32_hash_t!");
RT_DLLEXPORT rt_hash64 rtHashBytes(const void *begin, size_t count) {
return XXH3_64bits(begin, count);
return XXH64(begin, count, HASH64_SEED);
}

15
src/runtime/init.c
View File

@ -4,19 +4,23 @@
#include "file_tab.h"
#include "buffer_manager.h"
extern rt_cvar rt_MaxConcurrentAsyncIO;
extern rt_cvar rt_AssertEnabled;
extern rt_cvar rt_BufferMemoryBudget;
extern rt_cvar rt_FileTabCapacity;
extern rt_cvar rt_MaxConcurrentAsyncIO;
extern rt_cvar rt_TemporaryArenaSize;
extern rt_cvar rt_ResourceDirectory;
extern rt_cvar rt_ResourceCacheSize;
extern rt_cvar rt_MaxCachedResources;
extern rt_cvar rt_ResourceNamespaceSize;
extern rt_cvar rt_DisableResourceNamespaceLoad;
void RegisterRuntimeCVars(void) {
static void RegisterRuntimeCVars(void) {
rtRegisterCVAR(&rt_MaxConcurrentAsyncIO);
rtRegisterCVAR(&rt_AssertEnabled);
rtRegisterCVAR(&rt_BufferMemoryBudget);
rtRegisterCVAR(&rt_FileTabCapacity);
rtRegisterCVAR(&rt_MaxConcurrentAsyncIO);
rtRegisterCVAR(&rt_TemporaryArenaSize);
rtRegisterCVAR(&rt_ResourceDirectory);
rtRegisterCVAR(&rt_ResourceCacheSize);
rtRegisterCVAR(&rt_MaxCachedResources);
@ -25,6 +29,8 @@ void RegisterRuntimeCVars(void) {
}
extern void SetMainThreadId(void);
extern void ProcessEarlyEngineConfigs(void);
extern void InitStringStorage(void);
extern rt_result InitBufferManager(void);
extern void ShutdownBufferManager(void);
@ -39,6 +45,9 @@ extern rt_result InitTiming(void);
RT_DLLEXPORT rt_result rtInitRuntime(void) {
SetMainThreadId();
RegisterRuntimeCVars();
InitStringStorage();
ProcessEarlyEngineConfigs();
rt_result res;
if ((res = InitTiming()) != RT_SUCCESS) {

16
src/runtime/meson.build
View File

@ -1,5 +1,12 @@
# Runtime
runtime_deps = [thread_dep, m_dep, windowing_dep]
# Dependencies installed via wrap
inih_proj = subproject('inih', default_options: ['default_library=static', 'b_sanitize=none', 'utf-8_bom=true', 'multi-line_entries=true', 'report_line_numbers=true'])
inih_dep = inih_proj.get_variable('inih_dep')
lz4_proj = subproject('lz4', default_options: ['default_library=static', 'b_sanitize=none'])
lz4_dep = lz4_proj.get_variable('liblz4_dep')
xxhash_proj = subproject('xxhash', default_options: ['default_library=static', 'b_sanitize=none'])
xxhash_dep = xxhash_proj.get_variable('xxhash_dep')
runtime_deps = [thread_dep, m_dep, windowing_dep, inih_dep, lz4_dep, xxhash_dep]
runtime_incdirs = contrib_incdir
runtime_lib = library('rt',
# Project Sources
@ -18,6 +25,7 @@ runtime_lib = library('rt',
'mem_arena.h',
'resources.h',
'runtime.h',
'string_storage.h',
'threading.h',
'threading_helpers.hpp',
'timing.h',
@ -40,6 +48,7 @@ runtime_lib = library('rt',
'mem_arena.c',
'resource_manager.c',
'sprint.c',
'string_storage.c',
'text.c',
'threading_cond.c',
'threading_mutex.c',
@ -48,9 +57,6 @@ runtime_lib = library('rt',
'threading_thread.c',
'timing.c',
# Contrib Sources
contrib_dir / 'xxhash/xxhash.c',
contrib_dir / 'lz4/lz4.c',
dependencies : runtime_deps,
include_directories : [engine_incdir, runtime_incdirs],
c_pch : 'pch/rt_pch.h',

34
src/runtime/resource_manager.c
View File

@ -17,13 +17,13 @@
#include <string.h>
RT_CVAR_S(rt_ResourceDirectory, "The directory used for storing resources. Default: res", "res");
RT_CVAR_I(rt_ResourceCacheSize,
RT_CVAR_SZ(rt_ResourceCacheSize,
"The maximum amount of memory used for caching resources. Default: 512MB",
RT_MB(512));
RT_CVAR_I(rt_MaxCachedResources,
RT_CVAR_SZ(rt_MaxCachedResources,
"The maximum number of simultaneously cached resources. Default: 1024",
1024);
RT_CVAR_I(rt_ResourceNamespaceSize,
RT_CVAR_SZ(rt_ResourceNamespaceSize,
"The maximum number of resources that can exist. Default: 1.048.576",
1048576);
RT_CVAR_I(rt_DisableResourceNamespaceLoad,
@ -312,7 +312,7 @@ static void ShutdownResourceCache(void) {
/* NOTE(Kevin): Only call this while holding a write-lock on the cache.
* The function locks the reclaim heap lock itself. */
static bool FreeCacheSpace(size_t space) {
size_t free_space = (size_t)rt_ResourceCacheSize.i - _cache.current_size;
size_t free_space = rt_ResourceCacheSize.sz - _cache.current_size;
rtLockMutex(_cache.heap_lock);
while (free_space < space && !rtMinheapIsEmpty(&_cache.reclaim_heap)) {
rt_cached_resource_ref ref;
@ -336,7 +336,7 @@ static bool FreeCacheSpace(size_t space) {
res->size = 0;
/* Remove from lookup table */
size_t ht_size = (size_t)rt_MaxCachedResources.i * 2;
size_t ht_size = rt_MaxCachedResources.sz * 2;
for (size_t off = 0; off < ht_size; ++off) {
size_t slot = (ref.id + off) % ht_size;
if (_cache.resource_ids[slot] == ref.id) {
@ -352,7 +352,7 @@ static bool FreeCacheSpace(size_t space) {
}
static unsigned int FindCachedResource(rt_resource_id id) {
size_t ht_size = (size_t)rt_MaxCachedResources.i * 2;
size_t ht_size = rt_MaxCachedResources.sz * 2;
for (size_t off = 0; off < ht_size; ++off) {
size_t slot = (id + off) % ht_size;
if (_cache.resource_ids[slot] == id)
@ -378,7 +378,7 @@ static rt_resource *CacheResource(rt_resource_id id, const rt_resource *res) {
} else {
/* Insert into cache */
size_t total_size = sizeof(rt_resource) + GetResourceDataSize(res);
if (_cache.current_size + total_size >= (size_t)rt_ResourceCacheSize.i) {
if (_cache.current_size + total_size >= rt_ResourceCacheSize.sz) {
if (!FreeCacheSpace(total_size)) {
rtLog("RESMGR",
"Unable to reclaim %zu kB from the resource cache.",
@ -421,7 +421,7 @@ static rt_resource *CacheResource(rt_resource_id id, const rt_resource *res) {
/* Insert into lookup table */
bool inserted = false;
size_t ht_size = (size_t)rt_MaxCachedResources.i * 2;
size_t ht_size = rt_MaxCachedResources.sz * 2;
for (size_t off = 0; off < ht_size; ++off) {
size_t slot = (id + off) % ht_size;
if (_cache.resource_ids[slot] == RT_INVALID_RESOURCE_ID ||
@ -452,7 +452,7 @@ static void InsertPrefetchResourceIntoCache(rt_resource_id id,
return;
}
if (_cache.current_size + load_buffer_size >= (size_t)rt_ResourceCacheSize.i) {
if (_cache.current_size + load_buffer_size >= rt_ResourceCacheSize.sz) {
if (!FreeCacheSpace(load_buffer_size)) {
rtLog("RESMGR",
"Unable to reclaim %zu kB from the resource cache.",
@ -484,7 +484,7 @@ static void InsertPrefetchResourceIntoCache(rt_resource_id id,
/* Insert into lookup table */
bool inserted = false;
size_t ht_size = (size_t)rt_MaxCachedResources.i * 2;
size_t ht_size = rt_MaxCachedResources.sz * 2;
for (size_t off = 0; off < ht_size; ++off) {
size_t slot = (id + off) % ht_size;
if (_cache.resource_ids[slot] == RT_INVALID_RESOURCE_ID ||
@ -508,7 +508,7 @@ static void InsertPrefetchResourceIntoCache(rt_resource_id id,
static rt_resource_namespace _namespace;
static rt_result InitResourceNamespace(void) {
size_t size = (size_t)rt_ResourceNamespaceSize.i;
size_t size = rt_ResourceNamespaceSize.sz;
if (size == 0) {
rtReportError("RESMGR", "rt_ResourceNamespaceSize must be greater than 0.");
return RT_INVALID_VALUE;
@ -567,7 +567,7 @@ static void LoadNamespace(void) {
rt_hash64 entries_hash =
rtHashBytes(entries, sizeof(rt_namespace_file_entry) * header->num_entries);
if (entries_hash == header->checksum) {
size_t ns_size = (size_t)rt_ResourceNamespaceSize.i;
size_t ns_size = rt_ResourceNamespaceSize.sz;
for (uint32_t i = 0; i < header->num_entries; ++i) {
bool inserted = false;
for (size_t j = 0; j < ns_size; ++j) {
@ -610,7 +610,7 @@ static void LoadNamespace(void) {
static rt_resource_ref GetResourceRef(rt_resource_id id) {
rt_resource_ref ref = {.file = RT_INVALID_FILE_ID};
rtLockRead(&_namespace.lock);
size_t ns_size = (size_t)rt_ResourceNamespaceSize.i;
size_t ns_size = rt_ResourceNamespaceSize.sz;
for (size_t off = 0; off < ns_size; ++off) {
size_t at = (id + off) % ns_size;
if (_namespace.ids[at] == id) {
@ -772,7 +772,7 @@ RT_DLLEXPORT rt_result rtGetResource(rt_resource_id id, void *dest) {
RT_DLLEXPORT size_t rtGetResourceSize(rt_resource_id id) {
size_t size = 0;
rtLockRead(&_namespace.lock);
size_t ns_size = (size_t)rt_ResourceNamespaceSize.i;
size_t ns_size = rt_ResourceNamespaceSize.sz;
for (size_t off = 0; off < ns_size; ++off) {
size_t at = (id + off) % ns_size;
if (_namespace.ids[at] == id) {
@ -859,7 +859,7 @@ RT_DLLEXPORT rt_result rtCreateResources(uint32_t count,
const rt_resource *resources,
rt_resource_id *ids) {
rt_result result = RT_SUCCESS;
size_t ns_size = (size_t)rt_ResourceNamespaceSize.i;
size_t ns_size = rt_ResourceNamespaceSize.sz;
rt_write_batch writes = {.num_writes = 0};
rt_aio_handle write_handles[RT_WRITE_BATCH_MAX_SIZE];
@ -1090,7 +1090,7 @@ RT_DLLEXPORT void rtSaveResourceNamespace(void) {
rt_temp_arena temp = rtGetTemporaryArena(NULL, 0);
rtLockRead(&_namespace.lock);
uint32_t entry_count = 0;
for (size_t i = 0; i < (size_t)rt_ResourceNamespaceSize.i; ++i) {
for (size_t i = 0; i < rt_ResourceNamespaceSize.sz; ++i) {
if (_namespace.ids[i] != RT_INVALID_RESOURCE_ID)
++entry_count;
}
@ -1108,7 +1108,7 @@ RT_DLLEXPORT void rtSaveResourceNamespace(void) {
rt_namespace_file_header *header = buffer;
rt_namespace_file_entry *entries = (rt_namespace_file_entry *)(header + 1);
size_t at = 0;
for (size_t i = 0; i < (size_t)rt_ResourceNamespaceSize.i; ++i) {
for (size_t i = 0; i < rt_ResourceNamespaceSize.sz; ++i) {
if (_namespace.ids[i] != RT_INVALID_RESOURCE_ID) {
entries[at].id = _namespace.ids[i];
entries[at].ref = _namespace.refs[i];

120
src/runtime/string_storage.c Normal file
View File

@ -0,0 +1,120 @@
#include "string_storage.h"
#include <stdlib.h>
#include <string.h>
#define STRING_STORAGE_BUDGET RT_MB(1)
/* Must be greater than sizeof(rt_free_range) */
#define MIN_SPLIT_LENGTH 64
#define HEADER_MAGIC 0x1234567812345678uLL
typedef struct rt_free_range {
/* Begin is address of this struct */
size_t length;
struct rt_free_range *next;
} rt_free_range;
typedef struct {
size_t alloc_len;
uint64_t magic;
} rt_string_header;
static char _mem[STRING_STORAGE_BUDGET];
static rt_free_range *_first_free;
_Static_assert(sizeof(rt_free_range) < MIN_SPLIT_LENGTH, "Minimal split length must be greater than the size of a free list node.");
void InitStringStorage(void) {
_first_free = (rt_free_range *)& _mem[0];
_first_free->length = STRING_STORAGE_BUDGET;
_first_free->next = NULL;
}
RT_DLLEXPORT char *rtStoreString(const char *sz) {
size_t len = strlen(sz) + 1;
size_t alloc_len = len + sizeof(rt_string_header);
/* Look for a free range that is large enough */
rt_free_range *free_range = _first_free;
rt_free_range *prev = NULL;
while (free_range && free_range->length < alloc_len) {
prev = free_range;
free_range = free_range->next;
}
if (!free_range)
return NULL;
/* Should we split? */
if ((free_range->length - alloc_len) >= MIN_SPLIT_LENGTH) {
rt_free_range *split = (rt_free_range *)((char *)free_range + alloc_len);
split->length = free_range->length - alloc_len;
/* Enter into the linked list and remove the allocated range */
split->next = free_range->next;
if (prev)
prev->next = split;
else
_first_free = split;
} else {
/* Just remove us */
alloc_len = free_range->length;
if (prev)
prev->next = free_range->next;
else
_first_free = free_range->next;
}
char *ptr = (char *)free_range;
memcpy(ptr + sizeof(rt_string_header), sz, len);
rt_string_header *header = (rt_string_header*)ptr;
header->alloc_len = alloc_len;
header->magic = HEADER_MAGIC;
return ptr + sizeof(rt_string_header);
}
RT_DLLEXPORT void rtFreeString(char *storeStringRet) {
if (!storeStringRet)
return;
size_t len = strlen(storeStringRet) + 1;
if (((uintptr_t)storeStringRet < (uintptr_t)&_mem[sizeof(rt_string_header)]) ||
(((uintptr_t)storeStringRet + len) > (uintptr_t)&_mem[STRING_STORAGE_BUDGET - 1])) {
rtReportError("STRSTORAGE",
"Tried to free a string that is not stored in the string storage.");
return;
}
rt_string_header *header = (rt_string_header *)(storeStringRet - sizeof(rt_string_header));
if (header->magic != HEADER_MAGIC) {
rtReportError("STRSTORAGE", "Invalid header in string storage!");
return;
}
size_t alloc_len = header->alloc_len;
rt_free_range *free_range = (rt_free_range *)header;
free_range->length = alloc_len;
/* Search the place for inserting it */
rt_free_range *prev = _first_free;
if ((uintptr_t)prev < (uintptr_t)free_range) {
while (prev->next) {
if ((uintptr_t)prev->next > (uintptr_t)free_range)
break;
}
free_range->next = prev->next;
prev->next = free_range;
} else {
/* Swap */
rt_free_range *t = _first_free;
_first_free = free_range;
free_range = t;
prev = _first_free;
}
/* Check if we can merge */
while (((uintptr_t)prev + prev->length) == (uintptr_t)free_range) {
prev->length += alloc_len;
prev->next = free_range->next;
free_range = prev->next;
}
}

23
src/runtime/string_storage.h Normal file
View File

@ -0,0 +1,23 @@
#ifndef RT_STRING_STORAGE_H
#define RT_STRING_STORAGE_H
/* Memory management for strings.
* This should only be used for relatively short strings (<256 bytes)
* For large amounts of data, use the block allocator instead.
*/
#include "runtime.h"
#ifdef __cplusplus
extern "C" {
#endif
RT_DLLEXPORT char *rtStoreString(const char *sz);
RT_DLLEXPORT void rtFreeString(char *storeStringRet);
#ifdef __cplusplus
}
#endif
#endif

11
subprojects/inih.wrap Normal file
View File

@ -0,0 +1,11 @@
[wrap-file]
directory = inih-r57
source_url = https://github.com/benhoyt/inih/archive/r57.tar.gz
source_filename = inih-r57.tar.gz
source_hash = f03f98ca35c3adb56b2358573c8d3eda319ccd5287243d691e724b7eafa970b3
source_fallback_url = https://github.com/mesonbuild/wrapdb/releases/download/inih_r57-1/inih-r57.tar.gz
wrapdb_version = r57-1
[provide]
inih = inih_dep
inireader = INIReader_dep

12
subprojects/lz4.wrap Normal file
View File

@ -0,0 +1,12 @@
[wrap-file]
directory = lz4-1.9.4
source_url = https://github.com/lz4/lz4/archive/v1.9.4.tar.gz
source_filename = lz4-1.9.4.tgz
source_hash = 0b0e3aa07c8c063ddf40b082bdf7e37a1562bda40a0ff5272957f3e987e0e54b
patch_filename = lz4_1.9.4-2_patch.zip
patch_url = https://wrapdb.mesonbuild.com/v2/lz4_1.9.4-2/get_patch
patch_hash = 4f33456cce986167d23faf5d28a128e773746c10789950475d2155a7914630fb
wrapdb_version = 1.9.4-2
[provide]
liblz4 = liblz4_dep

13
subprojects/xxhash.wrap Normal file
View File

@ -0,0 +1,13 @@
[wrap-file]
directory = xxHash-0.8.2
source_url = https://github.com/Cyan4973/xxHash/archive/v0.8.2.tar.gz
source_filename = xxHash-0.8.2.tar.gz
source_hash = baee0c6afd4f03165de7a4e67988d16f0f2b257b51d0e3cb91909302a26a79c4
patch_filename = xxhash_0.8.2-1_patch.zip
patch_url = https://wrapdb.mesonbuild.com/v2/xxhash_0.8.2-1/get_patch
patch_hash = e721ef7a4c4ee0ade8b8440f6f7cb9f935b68e825249d74cb1c2503c53e68d25
source_fallback_url = https://github.com/mesonbuild/wrapdb/releases/download/xxhash_0.8.2-1/xxHash-0.8.2.tar.gz
wrapdb_version = 0.8.2-1
[provide]
libxxhash = xxhash_dep