Detailed Changelog - Digger1955/dxvk-gplasync-lowlatency GitHub Wiki

DXVK-GPLAsync-LowLatency 2.7-3 (DXVK-GPLALL 2.7-3)

Based on DXVK 2.7, DXVK GPLAsync 2.7-patch, DXVK Low Latency 2.7-commit cd329aa.

It consists of:

DXVK-GPLALL-GCC-WinMacLinux-SSE2-O3-LTO 2.7-3
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-GENERIC 2.7-3
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-INTEL 2.7-3
DXVK-GPLALL-MSVC-Windows-SSE2-O2-LTCG 2.7-3
DXVK-GPLALL-MSVC-Windows-AVX2-O2-LTCG-AMD64 2.7-3
DXVK-GPLALL-MSVC-Windows-SSE4.2-O2-LTCG-INTEL64 2.7-3
DXVK Native-GPLALL-GCC-SSE2-O3-LTO 2.7-3
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-GENERIC 2.7-3
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-INTEL 2.7-3
Source Code
dxvk.conf

Release Notes:

Reverted upstream DXVK 2.7 change which removes state cache starting from DXVK 2.7. Author - Laitinlok.
- Upstream DXVK state cache and DXVK GPLAsync state cache fixes for Async and GPL were ported in full, including options controls in dxvk.conf and environment variables.
  - State cache would be useful when used with Async without GPL to reduce stuttering in cases where shaders aren't compiling fast enough without GPL. Having state cache enabled should improve frame pacing which might benefit the latency of the application.
Enabled additional optimization (/Qpar) for MSVC SSE2-optimized (/arch:SSE2) builds of DXVK-GPLALL to futher increase performance in CPU-bound situations, speed up shader compilation. Author - Digger1955
- Note: /Qpar-report:2 and /Qvec-report:2 for MSVC builds are enabled for logging purposes and do not affect runtime performance in any way.

DXVK-GPLAsync-LowLatency 2.6.3-1 (DXVK-GPLALL 2.6.3-1)

Based on DXVK 2.6.2 and commits from DXVK 2.7, DXVK GPLAsync 2.6.2 and DXVK GPLAsync 2.7-patch, DXVK Low Latency 2.7-commit cd329aa.

It consists of:

DXVK-GPLALL-GCC-WinMacLinux-SSE2-O3-LTO 2.6.3-1
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-GENERIC 2.6.3-1
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-INTEL 2.6.3-1
DXVK-GPLALL-MSVC-Windows-SSE2-O2-LTCG 2.6.3-1
DXVK-GPLALL-MSVC-Windows-AVX2-O2-LTCG-AMD64 2.6.3-1
DXVK-GPLALL-MSVC-Windows-SSE4.2-O2-LTCG-INTEL64 2.6.3-1
DXVK Native-GPLALL-GCC-SSE2-O3-LTO 2.6.3-1
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-GENERIC 2.6.3-1
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-INTEL 2.6.3-1
Source Code
dxvk.conf

Release Notes:

IMPORTANT: DXVK-GPLALL 2.6.x version will be maintained for GPUs/drivers that do not have VK_KHR_maintenance5 and/or maxPushConstantsSize=256. Commits from DXVK, DXVK GPLAsync and DXVK Low Latency will be ported to DXVK-GPLALL 2.6.x, if possible. Also, DXVK-GPLALL 2.6.x will be recompiled from time to time, when new compiler versions with significant improvements are out.

First maintenance release of DXVK-GPLALL 2.6.x branch. Next maintenance releases will have less changes, due to more significant incompatibilities between DXVK 2.6.x and next DXVK versions.

Enabled additional optimization (/Qpar) for MSVC SSE2-optimized (/arch:SSE2) builds of DXVK-GPLALL to futher increase performance in CPU-bound situations, speed up shader compilation. Author - Digger1955
- Note: /Qpar-report:2 and /Qvec-report:2 for MSVC builds are enabled for logging purposes and do not affect runtime performance in any way.

List of ported and adapted upstream DXVK commits:

Note: The most significant and important change is Resource eviction PR with all fixes for it and defragmentation for Intel Battlemage GPUs

9afa095 - [d3d9] Fix GetAvailableTextureMem

06e5081 - [d3d9] Clarify vendor hack support

f4e67e5 - [d3d9] Don't change offset when skipping binding null VB

fe6a45e - [d3d9] Only show unsupported vendor hack warnings once

0038671 - [dxvk] Fall back to system memory when exceeding vram budget - Resource eviction

d10abad - [dxvk] Move resource allocator pointer to base class - Resource eviction

4ecaa93 - [dxvk] Allow passing null storage to relocation list - Resource eviction

d7251f9 - [dxvk] Migrate resources from system memory to VRAM on use - Resource eviction

1cf8bb0 - [dxvk] Periodically evict resources when under memory pressure - Resource eviction

8c32bef - [dxvk] Do not try to reclaim chunks from other memory pools - Resource eviction

cb92aee - [dxvk] Introduce new "move" access type - Resource eviction

6a78506 - [dxvk] Add config option to override memory budget - Resource eviction

9640b39 - [dxvk] Also defrag fallback memory types - Resource eviction

7668000 - [dxvk] Add proper heap property to enforce memory budget - Resource eviction

8ea8093 - [dxvk] Also defrag chunks that resources get evicted from - Resource eviction

39ccbc1 - [hud] Separate fallback chunks from mapped chunks - Resource eviction

680bf24 - [dxvk] Only consider one heap for device-local memory allocations - Resource eviction

d51422e - [dxvk] Be less aggressive about defragmenting fallback memory - Resource eviction

dedeee1 - [d3d9/dxgi] Add a force refresh rate config option - [d3d9/dxgi] Add a force refresh rate config option

78eded8 - [d3d8] Optimize D3D8 adapter format caching - [d3d9/dxgi] Add a force refresh rate config option

2316680 - [util] Disable direct image mapping for LEGO City Undercover

21e1d92 - [dxvk] Fix layers crashing when passing null swapchain to vkDestroySwapchainKHR

f1b60fd - [dxvk] Keep roughly 1% of device-local memory heaps unused

cb44610 - [util] Don't error out for otherwise unknown CPU architectures

d2c8e54 - [dxvk] Error out at build time if AVX is enabled

d2ee3ff - [d3d9] Remove support for d3d9ex specific depth formats

389702c - [dxvk] Enable memory defragmentation on Intel Battlemage GPUs

f6d790e - [util] Fix black screen on return from the A.I.M. options window

5270f64 - [spirv] Exclude unique types from type look-up

e668e33 - [d3d9] Remove the forceSwapchainMSAA option

9c5c310 - [util] Don't count losable resources for Astebreed

dd46e48 - [util] disable d3d9.textureMemory for Dungeon Lords

fae0af9 - [util] Disable losable resource tracking for SFC3

c2d59b0 - [util] Hide Nvidia GPU for Wargame: European Escalation

24fcf38 - [util] Splinter Cell config option tweaks

5c40598 - [util] Add configs for GTR - FIA GT Racing Game

2ac295f - [util] Enable deviceLossOnFocusLoss for Test Drive Unlimited 2

e940893 - [util] Explicitly flush log stream

b8db71b - [dxgi] Support presenting swap chains without a window

35aa75e - [d3d9] Only fail on DISCARD|READONLY locks of D3DPOOL_DEFAULT resources

629a5f0 - [util] Enable d3d9.hideNvidiaGpu for Perilous Warp

6a5544f - [dxvk] Fix isoline tessellation enum order

Ported D3D8 part and d3d9_bridge of upstream DXVK commits:

118094c - [d3d8/9] General and format helpers cleanup

6847d00 - [d3d8/9] Clean up CheckDeviceFormat and CreateImageSurface formats

List of ported and adapted DXVK Low Latency commits:

c29abbe - [dxvk] Collect GPU and V-Sync buffer stats - [hud] Latency Details: Show GPU buffer, V-Sync buffer, etc.

6d40102 - [hud] Add latency details - [hud] Latency Details: Show GPU buffer, V-Sync buffer, etc.

cd329aa - [dxvk] Track frame pacing buffer stats only on demand - [hud] Latency Details: Show GPU buffer, V-Sync buffer, etc.

DXVK-GPLAsync-LowLatency 2.7-2 (DXVK-GPLALL 2.7-2)

Based on DXVK 2.7, DXVK GPLAsync 2.7-patch, DXVK Low Latency 2.7-commit 1b5f3ac.

It consists of:

DXVK-GPLALL-GCC-WinMacLinux-SSE2-O3-LTO 2.7-2
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-GENERIC 2.7-2
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-INTEL 2.7-2
DXVK-GPLALL-MSVC-Windows-SSE2-O2-LTCG 2.7-2
DXVK-GPLALL-MSVC-Windows-AVX2-O2-LTCG-AMD64 2.7-2
DXVK-GPLALL-MSVC-Windows-SSE4.2-O2-LTCG-INTEL64 2.7-2
DXVK Native-GPLALL-GCC-SSE2-O3-LTO 2.7-2
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-GENERIC 2.7-2
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-INTEL 2.7-2
Source Code
dxvk.conf

Release Notes:

Lowered number of required draw calls for render target, after which asynchronous pipeline compilation for corresponding shader will be enabled, which leads to lower peak CPU load during shader compilation process, which leads to less stutters in both amount and longevity. Author - Digger1955, scientific info - Britt Yazel
- Based on tests results m_rtBindingFrameCount was changed from m_rtBindingFrameCount >= 5 to m_rtBindingFrameCount >= 2.
  - Note: Async graphical side effects are lessened, because of more shaders getting to use higher priority asynchronous pipeline compilation.

DXVK-GPLAsync-LowLatency 2.6.2-1 (DXVK-GPLALL 2.6.2-1)

Based on DXVK 2.6.2, DXVK GPLAsync 2.6.2 and DXVK GPLAsync 2.7-patch, DXVK Low Latency 2.7-commit 1b5f3ac.

It consists of:

DXVK-GPLALL-GCC-WinMacLinux-SSE2-O3-LTO 2.6.2-1
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-GENERIC 2.6.2-1
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-INTEL 2.6.2-1
DXVK-GPLALL-MSVC-Windows-SSE2-O2-LTCG 2.6.2-1
DXVK-GPLALL-MSVC-Windows-AVX2-O2-LTCG-AMD64 2.6.2-1
DXVK-GPLALL-MSVC-Windows-SSE4.2-O2-LTCG-INTEL64 2.6.2-1
DXVK Native-GPLALL-GCC-SSE2-O3-LTO 2.6.2-1
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-GENERIC 2.6.2-1
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-INTEL 2.6.2-1
Source Code
dxvk.conf

Release Notes:

Lowered number of required draw calls for render target, after which asynchronous pipeline compilation for corresponding shader will be enabled, which leads to lower peak CPU load during shader compilation process, which leads to less stutters in both amount and longevity. Author - Digger1955, scientific info - Britt Yazel
- Based on tests results m_rtBindingFrameCount was changed from m_rtBindingFrameCount >= 5 to m_rtBindingFrameCount >= 2.
  - Note: Async graphical side effects are lessened, because of more shaders getting to use higher priority asynchronous pipeline compilation.

DXVK-GPLAsync-LowLatency 2.7-1 (DXVK-GPLALL 2.7-1)

Based on DXVK 2.7, DXVK GPLAsync 2.7-patch, DXVK Low Latency 2.7.

It consists of:

DXVK-GPLALL-GCC-WinMacLinux-SSE2-O3-LTO 2.7-1
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-GENERIC 2.7-1
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-INTEL 2.7-1
DXVK-GPLALL-MSVC-Windows-SSE2-O2-LTCG 2.7-1
DXVK-GPLALL-MSVC-Windows-AVX2-O2-LTCG-AMD64 2.7-1
DXVK-GPLALL-MSVC-Windows-SSE4.2-O2-LTCG-INTEL64 2.7-1
DXVK Native-GPLALL-GCC-SSE2-O3-LTO 2.7-1
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-GENERIC 2.7-1
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-INTEL 2.7-1
Source Code
dxvk.conf

Release Notes:

Adjusted and implemented upstream DXVK change to HUD devinfo format. Author - Digger1955
- Reason: Backporting old devinfo format is problematic. New devinfo format is better for Linux/MacOS and tolerable on Windows with adjustments that have been made.

DXVK-GPLAsync-LowLatency 2.6.1-6 (DXVK-GPLALL 2.6.1-6)

Based on DXVK 2.6.1, DXVK GPLAsync 2.6.1, DXVK Low Latency 2.6.1.

It consists of:

DXVK-GPLALL-GCC-WinMacLinux-SSE2-O3-LTO 2.6.1-6
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-GENERIC 2.6.1-6
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO-INTEL 2.6.1-6
DXVK-GPLALL-MSVC-Windows-SSE2-O2-LTCG 2.6.1-6
DXVK-GPLALL-MSVC-Windows-AVX2-O2-LTCG-AMD64 2.6.1-6
DXVK-GPLALL-MSVC-Windows-SSE4.2-O2-LTCG-INTEL64 2.6.1-6
DXVK Native-GPLALL-GCC-SSE2-O3-LTO 2.6.1-6
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-GENERIC 2.6.1-6
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO-INTEL 2.6.1-6
Source Code
dxvk.conf

Release Notes:

GCC builds fixes only, MSVC builds users can ignore this release.

Fixed regression in GCC x86 builds, which led to use of 387 floating-point arithmetic instructions instead of sse instructions. Reported - ViNi-Arco, fixed - Digger1955.
- Added -msse and -msse2 to compiler_args. GCC requires either of them to be explicitly set in order to make -mfpmath=sse effective.
Enabled multi-threaded Link-Time Optimization (-flto=auto) for GCC builds. Author - Digger1955
- Does not affect compiler/linker output, speeds up LTO process. GCC requires -flto=auto to be explicitly set in order to activate multi-threading for LTO.
Provided GCC SSE4.2-optimized (-march=x86-64-v2) builds of DXVK-GPLALL with Link-Time Optimization (-flto=auto), -O3 optimization level, optimizations for Intel CPUs (-mtune=intel) and additional optimizations. Author - Digger1955
- Enabled optimizations for Intel CPUs (-mtune=intel) to futher increase performance in CPU-bound situations and to speed up shader compilation on Intel CPUs.
  - Note: For any other CPU in GCC SSE4.2-optimized builds -mtune=generic is used, because GCC does not have tuning options for AMD CPUs.
Provided GCC SSE4.2-optimized (-march=x86-64-v2) builds of DXVK-GPLALL with Link-Time Optimization (-flto=auto), -O3 optimization level, optimizations for up-to-date CPUs (-mtune=generic) and additional optimizations. Author - Digger1955
- Explicitly set -mtune=genericto enable optimizations for any up-to-date CPUs. Up-to-date CPUs in GCC 15.1 are: AMD Zen and Intel Haswell or newer.
  - Note: It was already active, due to GCC behaviour, which does set -mtune=generic, if you specify -mtune=x86-64-v2.

DXVK-GPLAsync-LowLatency 2.6.1-5 (DXVK-GPLALL 2.6.1-5)

Based on DXVK 2.6.1, DXVK GPLAsync 2.6.1, DXVK Low Latency 2.6.1.

It consists of:

DXVK-GPLALL-GCC-WinMacLinux-SSE2-O3-LTO 2.6.1-5
DXVK-GPLALL-GCC-WinMacLinux-SSE4.2-O3-LTO 2.6.1-5
DXVK-GPLALL-MSVC-Windows-SSE2-O2-LTCG 2.6.1-5
DXVK-GPLALL-MSVC-Windows-AVX2-O2-LTCG-AMD64 2.6.1-5
DXVK-GPLALL-MSVC-Windows-SSE4.2-O2-LTCG-INTEL64 2.6.1-5
DXVK Native-GPLALL-GCC-SSE2-O3-LTO 2.6.1-5
DXVK Native-GPLALL-GCC-SSE4.2-O3-LTO 2.6.1-5
Source Code
dxvk.conf

Release Notes:

Provided GCC SSE2-optimized (-march=x86-64, -mtune=x86-64) builds of DXVK-GPLALL with Link-Time Optimization (-flto) and -O3 optimization level. Author - Digger1955
- Enabled use of Link-Time Optimization (-flto) by GCC linker with additional optimizations and enabled -O3 optimization level to futher increase performance in CPU-bound situations, speed up shader compilation.
Provided GCC SSE4.2-optimized (-march=x86-64-v2, -mtune=x86-64-v2) builds of DXVK-GPLALL with Link-Time Optimization (-flto) and -O3 optimization level. They are replacing GCC AVX2-optimized builds. Author - Digger1955
- Use of -march=x86-64-v2, -mtune=x86-64-v2 allows to use GCC optimizations, such as -O3 optimization level and -flto, which results in higher performance and broader compatibility than -march=x86-64-v3, -mtune=x86-64-v3. GCC AVX2-optimized builds (-march=x86-64-v3, -mtune=x86-64-v3) crashed at application launch (known compiler toolchain bug).
Provided MSVC SSE2-optimized (/arch:SSE2) builds of DXVK-GPLALL with Link-Time Optimization (LTO, a.k.a. /LTCG), /O2 optimization level and additional optimizations. Author - Digger1955
- Enabled use of Link-Time Optimization (LTO, a.k.a. /LTCG) by MSVC linker with additional optimizations and enabled /O2 optimization level to futher increase performance in CPU-bound situations, speed up shader compilation. Enabled additional optimizations (/Ob3 and /Qpar) to futher increase performance in CPU-bound situations, speed up shader compilation.
Provided MSVC AVX2-optimized (/arch:AVX2) builds of DXVK-GPLALL with Link-Time Optimization (LTO, a.k.a. /LTCG), /O2 optimization level, optimizations for AMD CPUs in x64 DLLs (/favor:AMD64) and additional optimizations. Author - Digger1955
- Enabled use of specific optimizations for AMD CPUs (/favor:AMD64 and '/d2vzeroupper') by MSVC compiler to get higher performance in CPU-bound situations on AMD CPUs in x64 applications. Enabled additional optimizations (/Ob3 and /Qpar) to futher increase performance in CPU-bound situations, speed up shader compilation.
Provided MSVC SSE4.2-optimized (/arch:SSE4.2) builds of DXVK-GPLALL with Link-Time Optimization (LTO, a.k.a. /LTCG), /O2 optimization level, optimizations for Intel CPUs in x64 DLLs (/favor:INTEL64, a.k.a. /favor:EM64T) and additional optimizations. Author - Digger1955
- Enabled use of specific optimizations for Intel CPUs (/favor:INTEL64 a.k.a. /favor:EM64T) by MSVC compiler to get higher performance in CPU-bound situations on Intel CPUs in x64 applications. Enabled additional optimizations (/Ob3 and /Qpar) to futher increase performance in CPU-bound situations, speed up shader compilation.
  - Note: MSVC AVX2-optimized builds for Intel CPUs will not be provided. GCC/MSVC AVX2-optimized builds used with Intel CPUs exhibit degraded performance in power/temperature-limited cases due to downclocking/throttling. GCC/MSVC SSE4.2-optimized builds are providing the best possible performance for Intel CPUs.
- Important: Update your Visual C++ 2015-2022 Runtime to the latest version before using DXVK for Windows. Link for Visual C++ Redistributable Runtimes - https://www.techpowerup.com/download/visual-c-redistributable-runtime-package-all-in-one/

DXVK-GPLAsync-LowLatency 2.6.1-4 (DXVK-GPLALL 2.6.1-4)

Based on DXVK 2.6.1, DXVK GPLAsync 2.6.1, DXVK Low Latency 2.6.1.

It consists of:

DXVK-GPLALL-GCC-WinMacLinux 2.6.1-4
DXVK-GPLALL-GCC-WinMacLinux-AVX2 2.6.1-4
DXVK-GPLALL-MSVC-Windows 2.6.1-4
DXVK-GPLALL-MSVC-Windows-AVX2-O2-LTCG 2.6.1-4
DXVK Native-GPLALL-GCC 2.6.1-4
DXVK Native-GPLALL-GCC-AVX2 2.6.1-4
Source Code
dxvk.conf

Release Notes:

Changed minimal CPU requirements of GCC build from SSE3 to SSE2 (-march=x86-64, -mtune=x86-64). Author - Digger1955
- GCC build is tuned for SSE2 by default in upstream DXVK. Use of SSE3 instructions alone does not bring much benefit to DXVK and will have a negligible effect when CPU-bound (even at the fixed clock speed), and no effect whatsoever when GPU-bound.
  - Note: Upstream DXVK implies -march=x86-64 and -msse3, but -mtune=x86-64. This combination does not produce the most optimal result.
Disabled GPL by default. GPL still can be enabled by setting dxvk.enableGraphicsPipelineLibrary = True in dxvk.conf. Author - Digger1955
- Reason: Wiki
Restructured and tuned meson.build to guarantee proper output by various compilers. Author - Digger1955
- Enabled use -march=x86-64, -mtune=x86-64 and -march=x86-64-v3, -mtune=x86-64-v3 instead of separate instruction sets, corrected link_args structure.
Provided MSVC AVX2-optimized (/arch:AVX2) builds of DXVK-GPLALL with Link-Time Optimization (LTO, a.k.a /LTCG). Author - Digger1955
- Enabled use of Link-Time Optimization (LTO, a.k.a /LTCG) by MSVC linker with additional optimizations to futher increase performance in CPU-bound situations, decrease shader compilation stutter. DLLs size increased by 5-10% due to LTO.
  - Important: AVX2-optimized (/arch:AVX2) builds minimum requirements is support for AVX2 instructions. Best results will be observed on AMD CPUs starting from AMD Zen 3 generation. For Intel CPUs performance may degrade in some power/temperature-limited cases due to downclocking/throttling, but it depends on end-user configuration.
- Important: Update your Visual C++ 2015-2022 Runtime to the latest version before using DXVK for Windows. Link for Visual C++ Redistributable Runtimes - https://www.techpowerup.com/download/visual-c-redistributable-runtime-package-all-in-one/

DXVK-GPLAsync-LowLatency 2.6.1-3 (DXVK-GPLALL 2.6.1-3)

Based on DXVK 2.6.1, DXVK GPLAsync 2.6.1, DXVK Low Latency 2.6.1.

It consists of:

DXVK-GPLALL-LinuxMac 2.6.1-3
DXVK-GPLALL-Windows 2.6.1-3
DXVK-GPLALL-AVX2-Optimized-LinuxMac 2.6.1-3
DXVK-GPLALL-AVX2-Optimized-Windows 2.6.1-3
DXVK Native-GPLALL 2.6.1-3
DXVK Native-GPLALL-AVX2-Optimized 2.6.1-3
Source Code
dxvk.conf

Release Notes:

Provided Windows (MSVC) builds of DXVK-GPLALL. Author - Digger1955
- Windows (MSVC) builds minimum requirements is support for SSE2 instructions (Note: for Linux/MacOS - SSE3). It is the recommended DXVK build for using on Windows - it works better in CPU-bound situations, compiles shaders a little faster and is smaller in size in comparison to DXVK build for Linux/MacOS.
  - Note: PDBs are not provided.
- Important: Update your Visual C++ 2015-2022 Runtime to the latest version before using DXVK for Windows. Link for Visual C++ Redistributable Runtimes - https://www.techpowerup.com/download/visual-c-redistributable-runtime-package-all-in-one/
Provided AVX2 (x86-64-v3) optimized builds of DXVK-GPLALL. Author - Digger1955
- Enabled use of x86-64-v3 ISA by GCC compiler and AVX2 (/arch:AVX2) by MSVC compiler to increase performance in CPU-bound situations and decrease shader compilation stutter.
  - Important: AVX2 (x86-64-v3) builds minimum requirements is support for AVX2 instructions. Best results will be observed on AMD processors starting from AMD Zen 3 generation. For Intel processors performance may degrade due to downclocking/throttling, so it is not recommended for them.
- Enabled use of /O2 level of compiler optimization for Windows (MSVC) AVX2 builds to futher increase performance in CPU-bound situations and decrease shader compilation stutter.
  - Important: Builds with -O2 level of compiler optimization for Linux/MacOS (GCC) x86-64-v3 are crashing applications at launch, and therefore are not provided. Since builds are compiled using GitHub infrastructure there is nothing can be done to fix it for now.
Implemented use of "VK_EXT_load_store_op_none" Vulkan extension instead of "VK_KHR_load_store_op_none". Author - Digger1955
- They are identical, but "VK_EXT_load_store_op_none" available on a broader range of GPU drivers. This is especially important for mobile devices with Qualcomm Adreno GPUs, where it is not possible to change or update drivers.
Changed default number of used CPU logical threads from all to (CPULogicalThreads - 2). Author - Digger1955
- Reason: It leads to less stuttering when compiling shaders while playing, in comparison to using all CPU logical threads.
Reverted back upstream DXVK change to HUD format - devinfo now shows Device Name, Vulkan Headers version and Vulkan Driver version again. Author - Digger1955
- Reason: Inconsitent behaviour of new devinfo HUD format on different drivers, because of driver vendors.
Added fork tag to HUD - version now shows DXVK-GPLALL 2.6.1 on non-AVX2 builds and DXVK-GPLALL-AVX2-Optimized 2.6.1 on AVX2 builds. Author - Digger1955

DXVK-GPLAsync-LowLatency 2.6.1-2

Inital release.

Based on DXVK 2.6.1, DXVK GPLAsync 2.6.1, DXVK Low Latency 2.6.1.

It consists of:

DXVK-GPLAsync-LowLatency 2.6.1-2
DXVK Native-GPLAsync-LowLatency 2.6.1-2
Source Code
dxvk.conf

Release Notes:

Implemented Low Latency frame pacing mode that aims to greatly reduce latency with minimal impact in fps. Author - netborg-afps
Implemented Asynchronous pipeline compilation (Async) that aims to greatly reduce shader compilation stutter by not blocking the main thread when compiling async pipelines. Authors - jomihaka and Sporif
Implemented the ability to use both (together or separately) Graphics Pipeline Library (GPL) and Asynchronous pipeline compilation (Async) on DXVK 2.1 and later. Author - Ph42oN
Implemented default location for global DXVK configuration file (dxvk.conf) on Windows, Linux and MacOS. Author - Ph42oN
Implemented all of aforementioned in one DXVK package. Author - Digger1955