Emulator-Archive/ppsspp
1
0
Fork 0
mirror of https://github.com/hrydgard/ppsspp.git synced 2024-11-23 21:39:52 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Merge pull request #12882 from hrydgard/vulkan-fix-renderpass-opt

Browse Source 
Vulkan: Don't merge render passes where the second one begins with a clear.
This commit is contained in:
Henrik Rydgård 2020-05-11 00:18:59 +02:00 committed by GitHub
commit f23dd7635c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 21 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
Common/ColorConv.cpp
View File

@ -308,7 +308,7 @@ void ConvertRGBA565ToRGBA8888(u32 *dst32, const u16 *src, u32 numPixels) {
b = _mm_or_si128(_mm_slli_epi16(b, 3), _mm_srli_epi16(b, 2));
b = _mm_and_si128(b, mask8);
// Always set to 00FF 00FF.
// Always set alpha to 00FF 00FF.
__m128i a = _mm_slli_epi16(mask8, 8);
// Now combine them, RRGG RRGG and BBAA BBAA, and then interleave.
@ -472,36 +472,36 @@ void ConvertRGBA4444ToBGRA8888(u32 *dst32, const u16 *src, u32 numPixels) {
u8 *dst = (u8 *)dst32;
for (u32 x = 0; x < numPixels; x++) {
u16 c = src[x];
u32 r = c & 0x000f;
u32 g = (c >> 4) & 0x000f;
u32 b = (c >> 8) & 0x000f;
u32 a = (c >> 12) & 0x000f;
u32 r = Convert4To8(c & 0x000f);
u32 g = Convert4To8((c >> 4) & 0x000f);
u32 b = Convert4To8((c >> 8) & 0x000f);
u32 a = Convert4To8((c >> 12) & 0x000f);
dst[x] = (r << (16 + 4)) | (g << (8 + 4)) | (b << 4) | (a << (24 + 4));
dst[x] = (a << 24) | (r << 16) | (g << 8) | b;
}
}
void ConvertRGBA5551ToBGRA8888(u32 *dst, const u16 *src, u32 numPixels) {
for (u32 x = 0; x < numPixels; x++) {
u16 c = src[x];
u32 r = c & 0x001f;
u32 g = (c >> 5) & 0x001f;
u32 b = (c >> 10) & 0x001f;
u32 r = Convert5To8(c & 0x001f);
u32 g = Convert6To8((c >> 5) & 0x001f);
u32 b = Convert5To8((c >> 10) & 0x001f);
// We force an arithmetic shift to get the sign bits/
u32 a = ((s32)(s16)c) & 0xff000000;
dst[x] = (r << (16 + 3)) | (g << (8 + 3)) | (b << 3) | a;
dst[x] = a | (r << 16) | (g << 8) | b;
}
}
void ConvertRGB565ToBGRA8888(u32 *dst, const u16 *src, u32 numPixels) {
for (u32 x = 0; x < numPixels; x++) {
u16 c = src[x];
u32 r = c & 0x001f;
u32 g = (c >> 5) & 0x003f;
u32 b = (c >> 11) & 0x001f;
u32 r = Convert5To8(c & 0x001f);
u32 g = Convert6To8((c >> 5) & 0x003f);
u32 b = Convert5To8((c >> 11) & 0x001f);
dst[x] = (r << (16 + 3)) | (g << (8 + 2)) | (b << 3) | 0xFF000000;
dst[x] = 0xFF000000 | (r << 16) | (g << 8) | b;
}
}

2
GPU/Common/FramebufferCommon.cpp
View File

@ -1212,7 +1212,7 @@ void FramebufferManagerCommon::ResizeFramebufFBO(VirtualFramebuffer *vfb, int w,
}
}
// This is called from detected memcopies only. Not block transfers.
// This is called from detected memcopies and framebuffer initialization from VRAM. Not block transfers.
// MotoGP goes this path so we need to catch those copies here.
bool FramebufferManagerCommon::NotifyFramebufferCopy(u32 src, u32 dst, int size, bool isMemset, u32 skipDrawReason) {
if (size == 0) {

2
GPU/D3D11/TextureCacheD3D11.cpp
View File

@ -399,6 +399,8 @@ void TextureCacheD3D11::ApplyTextureFramebuffer(TexCacheEntry *entry, VirtualFra
shaderApply.ApplyBounds(gstate_c.vertBounds, gstate_c.curTextureXOffset, gstate_c.curTextureYOffset, xoff, yoff);
shaderApply.Use(depalShaderCache_->GetDepalettizeVertexShader(), depalShaderCache_->GetInputLayout());
ID3D11ShaderResourceView *nullTexture = nullptr;
context_->PSSetShaderResources(0, 1, &nullTexture); // In case the target was used in the last draw call. Happens in Sega Rally.
draw_->BindFramebufferAsRenderTarget(depalFBO, { Draw::RPAction::DONT_CARE, Draw::RPAction::DONT_CARE, Draw::RPAction::DONT_CARE });
context_->PSSetShaderResources(3, 1, &clutTexture);
context_->PSSetSamplers(3, 1, &stockD3D11.samplerPoint2DWrap);

5
ext/native/thin3d/VulkanQueueRunner.cpp
View File

@ -776,7 +776,10 @@ void VulkanQueueRunner::ApplyRenderPassMerge(std::vector<VKRStep *> &steps) {
if (steps[j]->dependencies.contains(touchedFramebuffers)) {
goto done_fb;
}
if (steps[j]->render.framebuffer == fb) {
if (steps[j]->render.framebuffer == fb &&
steps[j]->render.color != VKRRenderPassAction::CLEAR &&
steps[j]->render.depth != VKRRenderPassAction::CLEAR &&
steps[j]->render.stencil != VKRRenderPassAction::CLEAR) {
// ok. Now, if it's a render, slurp up all the commands
// and kill the step.
// Also slurp up any pretransitions.