rpcsx/rpcs3/Emu
kd-11 a668560c68 rsx: Use native half float types if available
- Emulating f16 with f32 is not ideal and requires a lot of value clamping
- Using native data type can significantly improve performance and accuracy
- With openGL, check for the compatible extensions NV_gpu_shader5 and
AMD_gpu_shader_half_float
- With Vulkan, enable this functionality in the deviceFeatures if
applicable. (VK_KHR_shader_float16_int8 extension)
- Temporarily disable hw fp16 for vulkan
2019-04-25 16:23:05 +03:00
..
Audio ALSA: disable recovery (experimental) 2019-01-18 16:49:17 +03:00
Cell LLVM DSL: expression matching (preview 2) 2019-04-25 03:33:18 +03:00
CPU LLVM DSL: expression matching (preview 2) 2019-04-25 03:33:18 +03:00
Io Adds class type to controller options 2019-02-27 18:13:19 +00:00
Memory Prefetch byteswapped opcodes in ppu interpreter 2019-04-11 17:47:52 +03:00
RSX rsx: Use native half float types if available 2019-04-25 16:23:05 +03:00
CMakeLists.txt Fix macOS compilation 2019-04-02 03:16:55 +03:00
GameInfo.h Fix true clear string container in GameInfo.h 2019-02-18 16:34:16 +03:00
IdManager.cpp Migration to named_thread<> 2018-10-19 22:22:35 +03:00
IdManager.h Migration to named_thread<> 2018-10-19 22:22:35 +03:00
IPC.h Cleanup semaphore<> (sema.h) and mutex.h (shared_mutex) 2018-09-03 23:00:36 +03:00
System.cpp DS3 pad handler 2019-03-18 19:05:02 +03:00
System.h rsx: Use native half float types if available 2019-04-25 16:23:05 +03:00
VFS.cpp Implement vfs::host::unlink 2019-04-10 13:58:12 +03:00
VFS.h Implement vfs::host::unlink 2019-04-10 13:58:12 +03:00