fabi/Xenia-Canary
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

use Sleep(0) instead of SwitchToThread, should waste less power and help the os with scheduling.

Browse Source 
PM4 buffer handling made a virtual member of commandprocessor, place the implementation/declaration into reusable macro files. this is probably the biggest boost here.
Optimized SET_CONSTANT/ LOAD_CONSTANT pm4 ops based on the register range they start writing at, this was also a nice boost

Expose X64 extension flags to code outside of x64 backend, so we can detect and use things like avx512, xop, avx2, etc in normal code
Add freelists for HIR structures to try to reduce the number of last level cache misses during optimization (currently disabled... fixme later)

Analyzed PGO feedback and reordered branches, uninlined functions, moved code out into different functions based on info from it in the PM4 functions, this gave like a 2% boost at best.

Added support for the db16cyc opcode, which is used often in xb360 spinlocks. before it was just being translated to nop, now on x64 we translate it to _mm_pause but may change that in the future to reduce cpu time wasted

texture util - all our divisors were powers of 2, instead we look up a shift. this made texture scaling slightly faster, more so on intel processors which seem to be worse at int divs. GetGuestTextureLayout is now a little faster, although it is still one of the heaviest functions in the emulator when scaling is on.

xe_unlikely_mutex was not a good choice for the guest clock lock, (running theory) on intel processors another thread may take a significant time to update the clock? maybe because of the uint64 division? really not sure, but switched it to xe_mutex. This fixed audio stutter that i had introduced to 1 or 2 games, fixed performance on that n64 rare game with the monkeys.
Took another crack at DMA implementation, another failure.
Instead of passing as a parameter, keep the ringbuffer reader as the first member of commandprocessor so it can be accessed through this
Added macro for noalias
Applied noalias to Memory::LookupHeap. This reduced the size of the executable by 7 kb.
Reworked kernel shim template, this shaved like 100kb off the exe and eliminated the indirect calls from the shim to the actual implementation. We still unconditionally generate string representations of kernel calls though :(, unless it is kHighFrequency

Add nvapi extensions support, currently unused. Will use CPUVISIBLE memory at some point
Inserted prefetches in a few places based on feedback from vtune.
Add native implementation of SHA int8 if all elements are the same

Vectorized comparisons for SetViewport, SetScissorRect
Vectorized ranged comparisons for WriteRegister
Add XE_MSVC_ASSUME
Move FormatInfo::name out of the structure, instead look up the name in a different table. Debug related data and critical runtime data are best kept apart
Templated UpdateSystemConstantValues based on ROV/RTV and primitive_polygonal
Add ArchFloatMask functions, these are for storing the results of floating point comparisons without doing costly float->int pipeline transfers (vucomiss/setb)
Use floatmasks in UpdateSystemConstantValues for checking if dirty, only transfer to int at end of function.
Instead of dirty |= (x == y) in UpdateSystemConstantValues, now we do dirty_u32 |= (x^y). if any of them are not equal, dirty_u32 will be nz, else if theyre all equal it will be zero. This is more friendly to register renaming and the lack of dependencies on EFLAGS lets the compiler reorder better
Add PrefetchSamplerParameters to D3D12TextureCache
use PrefetchSamplerParameters in UpdateBindings to eliminate cache misses that vtune detected

Add PrefetchTextureBinding to D3D12TextureCache
Prefetch texture bindings to get rid of more misses vtune detected (more accesses out of order with random strides)
Rewrote DMAC, still terrible though and have disabled it for now.
Replace tiny memcmp of 6 U64 in render_target_cache with inline loop, msvc fails to make it a loop and instead does a thunk to their memcmp function, which is optimized for larger sizes

PrefetchTextureBinding in AreActiveTextureSRVKeysUpToDate
Replace memcmp calls for pipelinedescription with handwritten cmp
Directly write some registers that dont have special handling in PM4 functions
Changed EstimateMaxY to try to eliminate mispredictions that vtune was reporting, msvc ended up turning the changed code into a series of blends

in ExecutePacketType3_EVENT_WRITE_EXT, instead of writing extents to an array on the stack and then doing xe_copy_and_swap_16 of the data to its dest, pre-swap each constant and then store those. msvc manages to unroll that into wider stores
stop logging XE_SWAP every time we receive XE_SWAP, stop logging the start and end of each viz query

Prefetch watch nodes in FireWatches based on feedback from vtune
Removed dead code from texture_info.cc
NOINLINE on GpuSwap, PGO builds did it so we should too.
This commit is contained in:
chss95cs@gmail.com
2022-09-11 14:14:48 -07:00
parent 9a6dd4cd6f
commit 20638c2e61
67 changed files with 3369 additions and 2184 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
src/xenia/gpu/texture_info.h
View File

@@ -181,7 +181,7 @@ inline xenos::TextureFormat DepthRenderTargetToTextureFormat(
}
}
enum class FormatType {
enum class FormatType : uint32_t {
// Uncompressed, and is also a ColorFormat.
kResolvable,
// Uncompressed, but resolve or memory export cannot be done to the format.
@@ -190,12 +190,12 @@ enum class FormatType {
};
struct FormatInfo {
xenos::TextureFormat format;
const char* name;
FormatType type;
uint32_t block_width;
uint32_t block_height;
uint32_t bits_per_pixel;
const xenos::TextureFormat format;
const FormatType type;
const uint32_t block_width;
const uint32_t block_height;
const uint32_t bits_per_pixel;
uint32_t bytes_per_block() const {
return block_width * block_height * bits_per_pixel / 8;
@@ -203,6 +203,20 @@ struct FormatInfo {
static const FormatInfo* Get(uint32_t gpu_format);
static const char* GetName(uint32_t gpu_format);
static const char* GetName(xenos::TextureFormat format) {
return GetName(static_cast<uint32_t>(format));
}
static unsigned char GetWidthShift(uint32_t gpu_format);
static unsigned char GetHeightShift(uint32_t gpu_format);
static unsigned char GetWidthShift(xenos::TextureFormat gpu_format) {
return GetWidthShift(static_cast<uint32_t>(gpu_format));
}
static unsigned char GetHeightShift(xenos::TextureFormat gpu_format) {
return GetHeightShift(static_cast<uint32_t>(gpu_format));
}
static const FormatInfo* Get(xenos::TextureFormat format) {
return Get(static_cast<uint32_t>(format));
}
@@ -259,7 +273,9 @@ struct TextureInfo {
const FormatInfo* format_info() const {
return FormatInfo::Get(static_cast<uint32_t>(format));
}
const char* format_name() const {
return FormatInfo::GetName(static_cast<uint32_t>(format));
}
bool is_compressed() const {
return format_info()->type == FormatType::kCompressed;
}
@@ -281,18 +297,6 @@ struct TextureInfo {
void GetMipSize(uint32_t mip, uint32_t* width, uint32_t* height) const;
// Get the memory location of a mip. offset_x and offset_y are in blocks.
uint32_t GetMipLocation(uint32_t mip, uint32_t* offset_x, uint32_t* offset_y,
bool is_guest) const;
static bool GetPackedTileOffset(uint32_t width, uint32_t height,
const FormatInfo* format_info,
int packed_tile, uint32_t* offset_x,
uint32_t* offset_y);
bool GetPackedTileOffset(int packed_tile, uint32_t* offset_x,
uint32_t* offset_y) const;
uint64_t hash() const;
bool operator==(const TextureInfo& other) const {
return std::memcmp(this, &other, sizeof(TextureInfo)) == 0;