swr/rast: Support render target mask instead of render target count
WIP to support read-only render targets. Reviewed-by: Bruce Cherniak <bruce.cherniak@intel.com>
This commit is contained in:
@@ -957,20 +957,26 @@ void SetupPipeline(DRAW_CONTEXT *pDC)
|
||||
(pState->state.depthStencilState.stencilTestEnable ||
|
||||
pState->state.depthStencilState.stencilWriteEnable)) ? true : false;
|
||||
|
||||
uint32_t numRTs = pState->state.psState.numRenderTargets;
|
||||
pState->state.colorHottileEnable = 0;
|
||||
pState->state.colorHottileEnable = pState->state.psState.renderTargetMask;
|
||||
|
||||
// Disable hottile for surfaces with no writes
|
||||
if (psState.pfnPixelShader != nullptr)
|
||||
{
|
||||
for (uint32_t rt = 0; rt < numRTs; ++rt)
|
||||
DWORD rt;
|
||||
uint32_t rtMask = pState->state.colorHottileEnable;
|
||||
while (_BitScanForward(&rt, rtMask))
|
||||
{
|
||||
pState->state.colorHottileEnable |=
|
||||
(!pState->state.blendState.renderTarget[rt].writeDisableAlpha ||
|
||||
!pState->state.blendState.renderTarget[rt].writeDisableRed ||
|
||||
!pState->state.blendState.renderTarget[rt].writeDisableGreen ||
|
||||
!pState->state.blendState.renderTarget[rt].writeDisableBlue) ? (1 << rt) : 0;
|
||||
rtMask &= ~(1 << rt);
|
||||
|
||||
if (pState->state.blendState.renderTarget[rt].writeDisableAlpha &&
|
||||
pState->state.blendState.renderTarget[rt].writeDisableRed &&
|
||||
pState->state.blendState.renderTarget[rt].writeDisableGreen &&
|
||||
pState->state.blendState.renderTarget[rt].writeDisableBlue)
|
||||
{
|
||||
pState->state.colorHottileEnable &= ~(1 << rt);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Setup depth quantization function
|
||||
if (pState->state.depthHottileEnable)
|
||||
{
|
||||
|
@@ -475,16 +475,15 @@ inline void SetupBarycentricCoeffs(BarycentricCoeffs *coeffs, const SWR_TRIANGLE
|
||||
coeffs->vCOneOverW = _simd_broadcast_ss(&work.OneOverW[2]);
|
||||
}
|
||||
|
||||
inline void SetupRenderBuffers(uint8_t *pColorBuffer[SWR_NUM_RENDERTARGETS], uint8_t **pDepthBuffer, uint8_t **pStencilBuffer, uint32_t colorBufferCount, RenderOutputBuffers &renderBuffers)
|
||||
inline void SetupRenderBuffers(uint8_t *pColorBuffer[SWR_NUM_RENDERTARGETS], uint8_t **pDepthBuffer, uint8_t **pStencilBuffer, uint32_t colorHotTileMask, RenderOutputBuffers &renderBuffers)
|
||||
{
|
||||
assert(colorBufferCount <= SWR_NUM_RENDERTARGETS);
|
||||
|
||||
if (pColorBuffer)
|
||||
|
||||
DWORD index;
|
||||
while (_BitScanForward(&index, colorHotTileMask))
|
||||
{
|
||||
for (uint32_t index = 0; index < colorBufferCount; index += 1)
|
||||
{
|
||||
pColorBuffer[index] = renderBuffers.pColor[index];
|
||||
}
|
||||
assert(index < SWR_NUM_RENDERTARGETS);
|
||||
colorHotTileMask &= ~(1 << index);
|
||||
pColorBuffer[index] = renderBuffers.pColor[index];
|
||||
}
|
||||
|
||||
if (pDepthBuffer)
|
||||
@@ -712,14 +711,16 @@ static INLINE void CalcSampleBarycentrics(const BarycentricCoeffs& coeffs, SWR_P
|
||||
|
||||
// Merge Output to 4x2 SIMD Tile Format
|
||||
INLINE void OutputMerger4x2(SWR_PS_CONTEXT &psContext, uint8_t* (&pColorBase)[SWR_NUM_RENDERTARGETS], uint32_t sample, const SWR_BLEND_STATE *pBlendState,
|
||||
const PFN_BLEND_JIT_FUNC (&pfnBlendFunc)[SWR_NUM_RENDERTARGETS], simdscalar &coverageMask, simdscalar depthPassMask, const uint32_t NumRT)
|
||||
const PFN_BLEND_JIT_FUNC (&pfnBlendFunc)[SWR_NUM_RENDERTARGETS], simdscalar &coverageMask, simdscalar depthPassMask, uint32_t renderTargetMask)
|
||||
{
|
||||
// type safety guaranteed from template instantiation in BEChooser<>::GetFunc
|
||||
const uint32_t rasterTileColorOffset = RasterTileColorOffset(sample);
|
||||
simdvector blendOut;
|
||||
|
||||
for(uint32_t rt = 0; rt < NumRT; ++rt)
|
||||
DWORD rt = 0;
|
||||
while (_BitScanForward(&rt, renderTargetMask))
|
||||
{
|
||||
renderTargetMask &= ~(1 << rt);
|
||||
uint8_t *pColorSample = pColorBase[rt] + rasterTileColorOffset;
|
||||
|
||||
const SWR_RENDER_TARGET_BLEND_STATE *pRTBlend = &pBlendState->renderTarget[rt];
|
||||
@@ -776,7 +777,7 @@ INLINE void OutputMerger4x2(SWR_PS_CONTEXT &psContext, uint8_t* (&pColorBase)[SW
|
||||
#if USE_8x2_TILE_BACKEND
|
||||
// Merge Output to 8x2 SIMD16 Tile Format
|
||||
INLINE void OutputMerger8x2(SWR_PS_CONTEXT &psContext, uint8_t* (&pColorBase)[SWR_NUM_RENDERTARGETS], uint32_t sample, const SWR_BLEND_STATE *pBlendState,
|
||||
const PFN_BLEND_JIT_FUNC(&pfnBlendFunc)[SWR_NUM_RENDERTARGETS], simdscalar &coverageMask, simdscalar depthPassMask, const uint32_t NumRT, const uint32_t colorBufferEnableMask, bool useAlternateOffset)
|
||||
const PFN_BLEND_JIT_FUNC(&pfnBlendFunc)[SWR_NUM_RENDERTARGETS], simdscalar &coverageMask, simdscalar depthPassMask, uint32_t renderTargetMask, bool useAlternateOffset)
|
||||
{
|
||||
// type safety guaranteed from template instantiation in BEChooser<>::GetFunc
|
||||
uint32_t rasterTileColorOffset = RasterTileColorOffset(sample);
|
||||
@@ -789,20 +790,27 @@ INLINE void OutputMerger8x2(SWR_PS_CONTEXT &psContext, uint8_t* (&pColorBase)[SW
|
||||
simdvector blendSrc;
|
||||
simdvector blendOut;
|
||||
|
||||
uint32_t colorBufferBit = 1;
|
||||
for (uint32_t rt = 0; rt < NumRT; rt += 1, colorBufferBit <<= 1)
|
||||
DWORD rt;
|
||||
while (_BitScanForward(&rt, renderTargetMask))
|
||||
{
|
||||
simdscalar *pColorSample = reinterpret_cast<simdscalar *>(pColorBase[rt] + rasterTileColorOffset);
|
||||
renderTargetMask &= ~(1 << rt);
|
||||
|
||||
const SWR_RENDER_TARGET_BLEND_STATE *pRTBlend = &pBlendState->renderTarget[rt];
|
||||
|
||||
if (colorBufferBit & colorBufferEnableMask)
|
||||
simdscalar* pColorSample;
|
||||
bool hotTileEnable = !pRTBlend->writeDisableAlpha || !pRTBlend->writeDisableRed || !pRTBlend->writeDisableGreen || !pRTBlend->writeDisableBlue;
|
||||
if (hotTileEnable)
|
||||
{
|
||||
pColorSample = reinterpret_cast<simdscalar *>(pColorBase[rt] + rasterTileColorOffset);
|
||||
blendSrc[0] = pColorSample[0];
|
||||
blendSrc[1] = pColorSample[2];
|
||||
blendSrc[2] = pColorSample[4];
|
||||
blendSrc[3] = pColorSample[6];
|
||||
}
|
||||
else
|
||||
{
|
||||
pColorSample = nullptr;
|
||||
}
|
||||
|
||||
{
|
||||
// pfnBlendFunc may not update all channels. Initialize with PS output.
|
||||
@@ -874,7 +882,7 @@ void BackendPixelRate(DRAW_CONTEXT *pDC, uint32_t workerId, uint32_t x, uint32_t
|
||||
SetupPixelShaderContext<T>(&psContext, samplePos, work);
|
||||
|
||||
uint8_t *pDepthBuffer, *pStencilBuffer;
|
||||
SetupRenderBuffers(psContext.pColorBuffer, &pDepthBuffer, &pStencilBuffer, state.psState.numRenderTargets, renderBuffers);
|
||||
SetupRenderBuffers(psContext.pColorBuffer, &pDepthBuffer, &pStencilBuffer, state.colorHottileEnable, renderBuffers);
|
||||
|
||||
AR_END(BESetup, 0);
|
||||
|
||||
@@ -994,9 +1002,9 @@ void BackendPixelRate(DRAW_CONTEXT *pDC, uint32_t workerId, uint32_t x, uint32_t
|
||||
|
||||
// broadcast the results of the PS to all passing pixels
|
||||
#if USE_8x2_TILE_BACKEND
|
||||
OutputMerger8x2(psContext, psContext.pColorBuffer, sample, &state.blendState,state.pfnBlendFunc, coverageMask, depthMask, state.psState.numRenderTargets, state.colorHottileEnable, useAlternateOffset);
|
||||
OutputMerger8x2(psContext, psContext.pColorBuffer, sample, &state.blendState,state.pfnBlendFunc, coverageMask, depthMask, state.psState.renderTargetMask, useAlternateOffset);
|
||||
#else // USE_8x2_TILE_BACKEND
|
||||
OutputMerger4x2(psContext, psContext.pColorBuffer, sample, &state.blendState, state.pfnBlendFunc, coverageMask, depthMask, state.psState.numRenderTargets);
|
||||
OutputMerger4x2(psContext, psContext.pColorBuffer, sample, &state.blendState, state.pfnBlendFunc, coverageMask, depthMask, state.psState.renderTargetMask);
|
||||
#endif // USE_8x2_TILE_BACKEND
|
||||
|
||||
if(!state.psState.forceEarlyZ && !T::bForcedSampleCount)
|
||||
@@ -1026,14 +1034,20 @@ Endtile:
|
||||
#if USE_8x2_TILE_BACKEND
|
||||
if (useAlternateOffset)
|
||||
{
|
||||
for (uint32_t rt = 0; rt < state.psState.numRenderTargets; ++rt)
|
||||
DWORD rt;
|
||||
uint32_t rtMask = state.colorHottileEnable;
|
||||
while (_BitScanForward(&rt, rtMask))
|
||||
{
|
||||
rtMask &= ~(1 << rt);
|
||||
psContext.pColorBuffer[rt] += (2 * KNOB_SIMD_WIDTH * FormatTraits<KNOB_COLOR_HOT_TILE_FORMAT>::bpp) / 8;
|
||||
}
|
||||
}
|
||||
#else
|
||||
for(uint32_t rt = 0; rt < state.psState.numRenderTargets; ++rt)
|
||||
DWORD rt;
|
||||
uint32_t rtMask = state.colorHottileEnable;
|
||||
while (_BitScanForward(&rt, rtMask))
|
||||
{
|
||||
rtMask &= ~(1 << rt);
|
||||
psContext.pColorBuffer[rt] += (KNOB_SIMD_WIDTH * FormatTraits<KNOB_COLOR_HOT_TILE_FORMAT>::bpp) / 8;
|
||||
}
|
||||
#endif
|
||||
|
@@ -55,7 +55,7 @@ void BackendSampleRate(DRAW_CONTEXT *pDC, uint32_t workerId, uint32_t x, uint32_
|
||||
SetupPixelShaderContext<T>(&psContext, samplePos, work);
|
||||
|
||||
uint8_t *pDepthBuffer, *pStencilBuffer;
|
||||
SetupRenderBuffers(psContext.pColorBuffer, &pDepthBuffer, &pStencilBuffer, state.psState.numRenderTargets, renderBuffers);
|
||||
SetupRenderBuffers(psContext.pColorBuffer, &pDepthBuffer, &pStencilBuffer, state.colorHottileEnable, renderBuffers);
|
||||
|
||||
AR_END(BESetup, 0);
|
||||
|
||||
@@ -198,9 +198,9 @@ void BackendSampleRate(DRAW_CONTEXT *pDC, uint32_t workerId, uint32_t x, uint32_
|
||||
// output merger
|
||||
AR_BEGIN(BEOutputMerger, pDC->drawId);
|
||||
#if USE_8x2_TILE_BACKEND
|
||||
OutputMerger8x2(psContext, psContext.pColorBuffer, sample, &state.blendState, state.pfnBlendFunc, vCoverageMask, depthPassMask, state.psState.numRenderTargets, state.colorHottileEnable, useAlternateOffset);
|
||||
OutputMerger8x2(psContext, psContext.pColorBuffer, sample, &state.blendState, state.pfnBlendFunc, vCoverageMask, depthPassMask, state.psState.renderTargetMask, useAlternateOffset);
|
||||
#else
|
||||
OutputMerger4x2(psContext, psContext.pColorBuffer, sample, &state.blendState, state.pfnBlendFunc, vCoverageMask, depthPassMask, state.psState.numRenderTargets);
|
||||
OutputMerger4x2(psContext, psContext.pColorBuffer, sample, &state.blendState, state.pfnBlendFunc, vCoverageMask, depthPassMask, state.psState.renderTargetMask);
|
||||
#endif
|
||||
|
||||
// do final depth write after all pixel kills
|
||||
@@ -227,14 +227,20 @@ void BackendSampleRate(DRAW_CONTEXT *pDC, uint32_t workerId, uint32_t x, uint32_
|
||||
#if USE_8x2_TILE_BACKEND
|
||||
if (useAlternateOffset)
|
||||
{
|
||||
for (uint32_t rt = 0; rt < state.psState.numRenderTargets; ++rt)
|
||||
DWORD rt;
|
||||
uint32_t rtMask = state.colorHottileEnable;
|
||||
while (_BitScanForward(&rt, rtMask))
|
||||
{
|
||||
rtMask &= ~(1 << rt);
|
||||
psContext.pColorBuffer[rt] += (2 * KNOB_SIMD_WIDTH * FormatTraits<KNOB_COLOR_HOT_TILE_FORMAT>::bpp) / 8;
|
||||
}
|
||||
}
|
||||
#else
|
||||
for (uint32_t rt = 0; rt < state.psState.numRenderTargets; ++rt)
|
||||
DWORD rt;
|
||||
uint32_t rtMask = state.colorHottileEnable;
|
||||
while (_BitScanForward(&rt, rtMask))
|
||||
{
|
||||
rtMask &= ~(1 << rt);
|
||||
psContext.pColorBuffer[rt] += (KNOB_SIMD_WIDTH * FormatTraits<KNOB_COLOR_HOT_TILE_FORMAT>::bpp) / 8;
|
||||
}
|
||||
#endif
|
||||
|
@@ -55,7 +55,7 @@ void BackendSingleSample(DRAW_CONTEXT *pDC, uint32_t workerId, uint32_t x, uint3
|
||||
SetupPixelShaderContext<T>(&psContext, samplePos, work);
|
||||
|
||||
uint8_t *pDepthBuffer, *pStencilBuffer;
|
||||
SetupRenderBuffers(psContext.pColorBuffer, &pDepthBuffer, &pStencilBuffer, state.psState.numRenderTargets, renderBuffers);
|
||||
SetupRenderBuffers(psContext.pColorBuffer, &pDepthBuffer, &pStencilBuffer, state.colorHottileEnable, renderBuffers);
|
||||
|
||||
AR_END(BESetup, 1);
|
||||
|
||||
@@ -183,9 +183,9 @@ void BackendSingleSample(DRAW_CONTEXT *pDC, uint32_t workerId, uint32_t x, uint3
|
||||
// output merger
|
||||
AR_BEGIN(BEOutputMerger, pDC->drawId);
|
||||
#if USE_8x2_TILE_BACKEND
|
||||
OutputMerger8x2(psContext, psContext.pColorBuffer, 0, &state.blendState, state.pfnBlendFunc, vCoverageMask, depthPassMask, state.psState.numRenderTargets, state.colorHottileEnable, useAlternateOffset);
|
||||
OutputMerger8x2(psContext, psContext.pColorBuffer, 0, &state.blendState, state.pfnBlendFunc, vCoverageMask, depthPassMask, state.psState.renderTargetMask, useAlternateOffset);
|
||||
#else
|
||||
OutputMerger4x2(psContext, psContext.pColorBuffer, 0, &state.blendState, state.pfnBlendFunc, vCoverageMask, depthPassMask, state.psState.numRenderTargets);
|
||||
OutputMerger4x2(psContext, psContext.pColorBuffer, 0, &state.blendState, state.pfnBlendFunc, vCoverageMask, depthPassMask, state.psState.renderTargetMask);
|
||||
#endif
|
||||
|
||||
// do final depth write after all pixel kills
|
||||
@@ -209,14 +209,20 @@ Endtile:
|
||||
#if USE_8x2_TILE_BACKEND
|
||||
if (useAlternateOffset)
|
||||
{
|
||||
for (uint32_t rt = 0; rt < state.psState.numRenderTargets; ++rt)
|
||||
DWORD rt;
|
||||
uint32_t rtMask = state.colorHottileEnable;
|
||||
while(_BitScanForward(&rt, rtMask))
|
||||
{
|
||||
rtMask &= ~(1 << rt);
|
||||
psContext.pColorBuffer[rt] += (2 * KNOB_SIMD_WIDTH * FormatTraits<KNOB_COLOR_HOT_TILE_FORMAT>::bpp) / 8;
|
||||
}
|
||||
}
|
||||
#else
|
||||
for (uint32_t rt = 0; rt < state.psState.numRenderTargets; ++rt)
|
||||
DWORD rt;
|
||||
uint32_t rtMask = state.colorHottileEnable;
|
||||
while (_BitScanForward(&rt, rtMask))
|
||||
{
|
||||
rtMask &= ~(1 << rt);
|
||||
psContext.pColorBuffer[rt] += (KNOB_SIMD_WIDTH * FormatTraits<KNOB_COLOR_HOT_TILE_FORMAT>::bpp) / 8;
|
||||
}
|
||||
#endif
|
||||
|
@@ -42,9 +42,9 @@ extern PFN_WORK_FUNC gRasterizerFuncs[SWR_MULTISAMPLE_TYPE_COUNT][2][2][SWR_INPU
|
||||
template <uint32_t numSamples = 1>
|
||||
void GetRenderHotTiles(DRAW_CONTEXT *pDC, uint32_t macroID, uint32_t x, uint32_t y, RenderOutputBuffers &renderBuffers, uint32_t renderTargetArrayIndex);
|
||||
template <typename RT>
|
||||
void StepRasterTileX(uint32_t MaxRT, RenderOutputBuffers &buffers);
|
||||
void StepRasterTileX(uint32_t colorHotTileMask, RenderOutputBuffers &buffers);
|
||||
template <typename RT>
|
||||
void StepRasterTileY(uint32_t MaxRT, RenderOutputBuffers &buffers, RenderOutputBuffers &startBufferRow);
|
||||
void StepRasterTileY(uint32_t colorHotTileMask, RenderOutputBuffers &buffers, RenderOutputBuffers &startBufferRow);
|
||||
|
||||
#define MASKTOVEC(i3,i2,i1,i0) {-i0,-i1,-i2,-i3}
|
||||
static const __m256d gMaskToVecpd[] =
|
||||
@@ -1281,7 +1281,7 @@ void RasterizeTriangle(DRAW_CONTEXT* pDC, uint32_t workerId, uint32_t macroTile,
|
||||
{
|
||||
vEdgeFix16[e] = _mm256_add_pd(vEdgeFix16[e], _mm256_set1_pd(rastEdges[e].stepRasterTileX));
|
||||
}
|
||||
StepRasterTileX<RT>(state.psState.numRenderTargets, renderBuffers);
|
||||
StepRasterTileX<RT>(state.colorHottileEnable, renderBuffers);
|
||||
}
|
||||
|
||||
// step to the next tile in Y
|
||||
@@ -1289,7 +1289,7 @@ void RasterizeTriangle(DRAW_CONTEXT* pDC, uint32_t workerId, uint32_t macroTile,
|
||||
{
|
||||
vEdgeFix16[e] = _mm256_add_pd(vStartOfRowEdge[e], _mm256_set1_pd(rastEdges[e].stepRasterTileY));
|
||||
}
|
||||
StepRasterTileY<RT>(state.psState.numRenderTargets, renderBuffers, currentRenderBufferRow);
|
||||
StepRasterTileY<RT>(state.colorHottileEnable, renderBuffers, currentRenderBufferRow);
|
||||
}
|
||||
|
||||
AR_END(BERasterizeTriangle, 1);
|
||||
@@ -1348,10 +1348,12 @@ void GetRenderHotTiles(DRAW_CONTEXT *pDC, uint32_t macroID, uint32_t tileX, uint
|
||||
}
|
||||
|
||||
template <typename RT>
|
||||
INLINE void StepRasterTileX(uint32_t NumRT, RenderOutputBuffers &buffers)
|
||||
INLINE void StepRasterTileX(uint32_t colorHotTileMask, RenderOutputBuffers &buffers)
|
||||
{
|
||||
for(uint32_t rt = 0; rt < NumRT; ++rt)
|
||||
DWORD rt = 0;
|
||||
while (_BitScanForward(&rt, colorHotTileMask))
|
||||
{
|
||||
colorHotTileMask &= ~(1 << rt);
|
||||
buffers.pColor[rt] += RT::colorRasterTileStep;
|
||||
}
|
||||
|
||||
@@ -1360,10 +1362,12 @@ INLINE void StepRasterTileX(uint32_t NumRT, RenderOutputBuffers &buffers)
|
||||
}
|
||||
|
||||
template <typename RT>
|
||||
INLINE void StepRasterTileY(uint32_t NumRT, RenderOutputBuffers &buffers, RenderOutputBuffers &startBufferRow)
|
||||
INLINE void StepRasterTileY(uint32_t colorHotTileMask, RenderOutputBuffers &buffers, RenderOutputBuffers &startBufferRow)
|
||||
{
|
||||
for(uint32_t rt = 0; rt < NumRT; ++rt)
|
||||
DWORD rt = 0;
|
||||
while (_BitScanForward(&rt, colorHotTileMask))
|
||||
{
|
||||
colorHotTileMask &= ~(1 << rt);
|
||||
startBufferRow.pColor[rt] += RT::colorRasterTileRowStep;
|
||||
buffers.pColor[rt] = startBufferRow.pColor[rt];
|
||||
}
|
||||
|
@@ -1139,7 +1139,7 @@ struct SWR_PS_STATE
|
||||
uint32_t writesODepth : 1; // pixel shader writes to depth
|
||||
uint32_t usesSourceDepth : 1; // pixel shader reads depth
|
||||
uint32_t shadingRate : 2; // shading per pixel / sample / coarse pixel
|
||||
uint32_t numRenderTargets : 4; // number of render target outputs in use (0-8)
|
||||
uint32_t renderTargetMask : 8; // number of render target outputs in use (0-8)
|
||||
uint32_t posOffset : 2; // type of offset (none, sample, centroid) to add to pixel position
|
||||
uint32_t barycentricsMask : 3; // which type(s) of barycentric coords does the PS interpolate attributes with
|
||||
uint32_t usesUAV : 1; // pixel shader accesses UAV
|
||||
|
@@ -1461,7 +1461,7 @@ swr_update_derived(struct pipe_context *pipe,
|
||||
psState.writesODepth = ctx->fs->info.base.writes_z;
|
||||
psState.usesSourceDepth = ctx->fs->info.base.reads_z;
|
||||
psState.shadingRate = SWR_SHADING_RATE_PIXEL;
|
||||
psState.numRenderTargets = ctx->framebuffer.nr_cbufs;
|
||||
psState.renderTargetMask = (1 << ctx->framebuffer.nr_cbufs) - 1;
|
||||
psState.posOffset = SWR_PS_POSITION_SAMPLE_NONE;
|
||||
uint32_t barycentricsMask = 0;
|
||||
#if 0
|
||||
|
Reference in New Issue
Block a user