884b4e5fd3
* Initial non 2D textures support - Shaders still need to be changed - Some types aren't yet implemented * Start implementing texture instructions suffixes Fix wrong texture type with cube and TEXS Also support array textures in TEX and TEX.B Clean up TEX and TEXS coords managment Fix TEXS.LL with non-2d textures Implement TEX.AOFFI Get the right arguments for TEX, TEXS and TLDS Also, store suffix operands in appropriate values to support multiple suffix combinaisons * Support depth in read/writeTexture Also support WrapR and detect mipmap * Proper cube map textures support + fix TEXS.LZ * Implement depth compare * some code clean up * Implement CubeMap textures in OGLTexture.Create * Implement TLD4 and TLD4S * Add Texture 1D support * updates comments * fix some code style issues * Fix some nits + rename some things to be less confusing * Remove GetSuffix local functions * AOFFI => AOffI * TextureType => GalTextureTarget * finish renaming TextureType to TextureTarget * Disable LL, LZ and LB support in the decompiler This needs more work at the GL level (GLSL implementation should be right) * Revert "Disable LL, LZ and LB support in the decompiler" This reverts commit 64536c3d9f673645faff3152838d1413c3203395. * Fix TEXS ARRAY_2D index * ImageFormat depth should be 1 for all image format * Fix shader build issues with sampler1DShadow and texture * Fix DC & AOFFI combinaison with TEX/TEXS * Support AOFFI with TLD4 and TLD4S * Fix shader compilation error for TLD4.AOFFI with no DC * Fix binding isuses on the 2d copy engine TODO: support 2d array copy * Support 2D array copy operation in the 2D engine This make every copy right in the GPU side. Thie CPU copy probably needs to be updated * Implement GetGpuSize + fix somes issues with 2d engine copies TODO: mipmap level in it * Don't throw an exception in the layer handling * Fix because of rebase * Reject 2d layers of non textures in 2d copy engine * Add 3D textures and mipmap support on BlockLinearSwizzle * Fix naming on new BitUtils methods * gpu cache: Make sure to invalidate textures that doesn't have the same target * Add the concept of layer count for array instead of using depth Also cleanup GetGpuSize as Swizzle can compute the size with mipmap * Support multi layer with mip map in ReadTexture * Add more check for cache invalidation & remove cubemap and cubemap array code for now Also fix compressed 2d array * Fix texelFetchOffset shader build error * Start looking into cube map again Also add some way to log write in register in engines * fix write register log levles * Remove debug logs in WriteRegister * Disable AOFFI support on non NVIDIA drivers * Fix code align
259 lines
No EOL
8.7 KiB
C#
259 lines
No EOL
8.7 KiB
C#
using Ryujinx.Common.Logging;
|
|
using Ryujinx.Graphics.Gal;
|
|
using Ryujinx.Graphics.Memory;
|
|
using Ryujinx.Graphics.Texture;
|
|
|
|
namespace Ryujinx.Graphics.Graphics3d
|
|
{
|
|
class NvGpuEngine2d : INvGpuEngine
|
|
{
|
|
private enum CopyOperation
|
|
{
|
|
SrcCopyAnd,
|
|
RopAnd,
|
|
Blend,
|
|
SrcCopy,
|
|
Rop,
|
|
SrcCopyPremult,
|
|
BlendPremult
|
|
}
|
|
|
|
public int[] Registers { get; private set; }
|
|
|
|
private NvGpu Gpu;
|
|
|
|
public NvGpuEngine2d(NvGpu Gpu)
|
|
{
|
|
this.Gpu = Gpu;
|
|
|
|
Registers = new int[0x238];
|
|
}
|
|
|
|
public void CallMethod(NvGpuVmm Vmm, GpuMethodCall MethCall)
|
|
{
|
|
WriteRegister(MethCall);
|
|
|
|
if ((NvGpuEngine2dReg)MethCall.Method == NvGpuEngine2dReg.BlitSrcYInt)
|
|
{
|
|
TextureCopy(Vmm);
|
|
}
|
|
}
|
|
|
|
private void TextureCopy(NvGpuVmm Vmm)
|
|
{
|
|
CopyOperation Operation = (CopyOperation)ReadRegister(NvGpuEngine2dReg.CopyOperation);
|
|
|
|
int DstFormat = ReadRegister(NvGpuEngine2dReg.DstFormat);
|
|
bool DstLinear = ReadRegister(NvGpuEngine2dReg.DstLinear) != 0;
|
|
int DstWidth = ReadRegister(NvGpuEngine2dReg.DstWidth);
|
|
int DstHeight = ReadRegister(NvGpuEngine2dReg.DstHeight);
|
|
int DstDepth = ReadRegister(NvGpuEngine2dReg.DstDepth);
|
|
int DstLayer = ReadRegister(NvGpuEngine2dReg.DstLayer);
|
|
int DstPitch = ReadRegister(NvGpuEngine2dReg.DstPitch);
|
|
int DstBlkDim = ReadRegister(NvGpuEngine2dReg.DstBlockDimensions);
|
|
|
|
int SrcFormat = ReadRegister(NvGpuEngine2dReg.SrcFormat);
|
|
bool SrcLinear = ReadRegister(NvGpuEngine2dReg.SrcLinear) != 0;
|
|
int SrcWidth = ReadRegister(NvGpuEngine2dReg.SrcWidth);
|
|
int SrcHeight = ReadRegister(NvGpuEngine2dReg.SrcHeight);
|
|
int SrcDepth = ReadRegister(NvGpuEngine2dReg.SrcDepth);
|
|
int SrcLayer = ReadRegister(NvGpuEngine2dReg.SrcLayer);
|
|
int SrcPitch = ReadRegister(NvGpuEngine2dReg.SrcPitch);
|
|
int SrcBlkDim = ReadRegister(NvGpuEngine2dReg.SrcBlockDimensions);
|
|
|
|
int DstBlitX = ReadRegister(NvGpuEngine2dReg.BlitDstX);
|
|
int DstBlitY = ReadRegister(NvGpuEngine2dReg.BlitDstY);
|
|
int DstBlitW = ReadRegister(NvGpuEngine2dReg.BlitDstW);
|
|
int DstBlitH = ReadRegister(NvGpuEngine2dReg.BlitDstH);
|
|
|
|
long BlitDuDx = ReadRegisterFixed1_31_32(NvGpuEngine2dReg.BlitDuDxFract);
|
|
long BlitDvDy = ReadRegisterFixed1_31_32(NvGpuEngine2dReg.BlitDvDyFract);
|
|
|
|
long SrcBlitX = ReadRegisterFixed1_31_32(NvGpuEngine2dReg.BlitSrcXFract);
|
|
long SrcBlitY = ReadRegisterFixed1_31_32(NvGpuEngine2dReg.BlitSrcYFract);
|
|
|
|
GalImageFormat SrcImgFormat = ImageUtils.ConvertSurface((GalSurfaceFormat)SrcFormat);
|
|
GalImageFormat DstImgFormat = ImageUtils.ConvertSurface((GalSurfaceFormat)DstFormat);
|
|
|
|
GalMemoryLayout SrcLayout = GetLayout(SrcLinear);
|
|
GalMemoryLayout DstLayout = GetLayout(DstLinear);
|
|
|
|
int SrcBlockHeight = 1 << ((SrcBlkDim >> 4) & 0xf);
|
|
int DstBlockHeight = 1 << ((DstBlkDim >> 4) & 0xf);
|
|
|
|
long SrcAddress = MakeInt64From2xInt32(NvGpuEngine2dReg.SrcAddress);
|
|
long DstAddress = MakeInt64From2xInt32(NvGpuEngine2dReg.DstAddress);
|
|
|
|
long SrcKey = Vmm.GetPhysicalAddress(SrcAddress);
|
|
long DstKey = Vmm.GetPhysicalAddress(DstAddress);
|
|
|
|
bool IsSrcLayered = false;
|
|
bool IsDstLayered = false;
|
|
|
|
GalTextureTarget SrcTarget = GalTextureTarget.TwoD;
|
|
|
|
if (SrcDepth != 0)
|
|
{
|
|
SrcTarget = GalTextureTarget.TwoDArray;
|
|
SrcDepth++;
|
|
IsSrcLayered = true;
|
|
}
|
|
else
|
|
{
|
|
SrcDepth = 1;
|
|
}
|
|
|
|
GalTextureTarget DstTarget = GalTextureTarget.TwoD;
|
|
|
|
if (DstDepth != 0)
|
|
{
|
|
DstTarget = GalTextureTarget.TwoDArray;
|
|
DstDepth++;
|
|
IsDstLayered = true;
|
|
}
|
|
else
|
|
{
|
|
DstDepth = 1;
|
|
}
|
|
|
|
GalImage SrcTexture = new GalImage(
|
|
SrcWidth,
|
|
SrcHeight,
|
|
1, SrcDepth, 1,
|
|
SrcBlockHeight, 1,
|
|
SrcLayout,
|
|
SrcImgFormat,
|
|
SrcTarget);
|
|
|
|
GalImage DstTexture = new GalImage(
|
|
DstWidth,
|
|
DstHeight,
|
|
1, DstDepth, 1,
|
|
DstBlockHeight, 1,
|
|
DstLayout,
|
|
DstImgFormat,
|
|
DstTarget);
|
|
|
|
SrcTexture.Pitch = SrcPitch;
|
|
DstTexture.Pitch = DstPitch;
|
|
|
|
long GetLayerOffset(GalImage Image, int Layer)
|
|
{
|
|
int TargetMipLevel = Image.MaxMipmapLevel <= 1 ? 1 : Image.MaxMipmapLevel - 1;
|
|
return ImageUtils.GetLayerOffset(Image, TargetMipLevel) * Layer;
|
|
}
|
|
|
|
int SrcLayerIndex = -1;
|
|
|
|
if (IsSrcLayered && Gpu.ResourceManager.TryGetTextureLayer(SrcKey, out SrcLayerIndex) && SrcLayerIndex != 0)
|
|
{
|
|
SrcKey = SrcKey - GetLayerOffset(SrcTexture, SrcLayerIndex);
|
|
}
|
|
|
|
int DstLayerIndex = -1;
|
|
|
|
if (IsDstLayered && Gpu.ResourceManager.TryGetTextureLayer(DstKey, out DstLayerIndex) && DstLayerIndex != 0)
|
|
{
|
|
DstKey = DstKey - GetLayerOffset(DstTexture, DstLayerIndex);
|
|
}
|
|
|
|
Gpu.ResourceManager.SendTexture(Vmm, SrcKey, SrcTexture);
|
|
Gpu.ResourceManager.SendTexture(Vmm, DstKey, DstTexture);
|
|
|
|
if (IsSrcLayered && SrcLayerIndex == -1)
|
|
{
|
|
for (int Layer = 0; Layer < SrcTexture.LayerCount; Layer++)
|
|
{
|
|
Gpu.ResourceManager.SetTextureArrayLayer(SrcKey + GetLayerOffset(SrcTexture, Layer), Layer);
|
|
}
|
|
|
|
SrcLayerIndex = 0;
|
|
}
|
|
|
|
if (IsDstLayered && DstLayerIndex == -1)
|
|
{
|
|
for (int Layer = 0; Layer < DstTexture.LayerCount; Layer++)
|
|
{
|
|
Gpu.ResourceManager.SetTextureArrayLayer(DstKey + GetLayerOffset(DstTexture, Layer), Layer);
|
|
}
|
|
|
|
DstLayerIndex = 0;
|
|
}
|
|
|
|
int SrcBlitX1 = (int)(SrcBlitX >> 32);
|
|
int SrcBlitY1 = (int)(SrcBlitY >> 32);
|
|
|
|
int SrcBlitX2 = (int)(SrcBlitX + DstBlitW * BlitDuDx >> 32);
|
|
int SrcBlitY2 = (int)(SrcBlitY + DstBlitH * BlitDvDy >> 32);
|
|
|
|
Gpu.Renderer.RenderTarget.Copy(
|
|
SrcTexture,
|
|
DstTexture,
|
|
SrcKey,
|
|
DstKey,
|
|
SrcLayerIndex,
|
|
DstLayerIndex,
|
|
SrcBlitX1,
|
|
SrcBlitY1,
|
|
SrcBlitX2,
|
|
SrcBlitY2,
|
|
DstBlitX,
|
|
DstBlitY,
|
|
DstBlitX + DstBlitW,
|
|
DstBlitY + DstBlitH);
|
|
|
|
//Do a guest side copy aswell. This is necessary when
|
|
//the texture is modified by the guest, however it doesn't
|
|
//work when resources that the gpu can write to are copied,
|
|
//like framebuffers.
|
|
|
|
// FIXME: SUPPORT MULTILAYER CORRECTLY HERE (this will cause weird stuffs on the first layer)
|
|
ImageUtils.CopyTexture(
|
|
Vmm,
|
|
SrcTexture,
|
|
DstTexture,
|
|
SrcAddress,
|
|
DstAddress,
|
|
SrcBlitX1,
|
|
SrcBlitY1,
|
|
DstBlitX,
|
|
DstBlitY,
|
|
DstBlitW,
|
|
DstBlitH);
|
|
|
|
Vmm.IsRegionModified(DstKey, ImageUtils.GetSize(DstTexture), NvGpuBufferType.Texture);
|
|
}
|
|
|
|
private static GalMemoryLayout GetLayout(bool Linear)
|
|
{
|
|
return Linear
|
|
? GalMemoryLayout.Pitch
|
|
: GalMemoryLayout.BlockLinear;
|
|
}
|
|
|
|
private long MakeInt64From2xInt32(NvGpuEngine2dReg Reg)
|
|
{
|
|
return
|
|
(long)Registers[(int)Reg + 0] << 32 |
|
|
(uint)Registers[(int)Reg + 1];
|
|
}
|
|
|
|
private void WriteRegister(GpuMethodCall MethCall)
|
|
{
|
|
Registers[MethCall.Method] = MethCall.Argument;
|
|
}
|
|
|
|
private long ReadRegisterFixed1_31_32(NvGpuEngine2dReg Reg)
|
|
{
|
|
long Low = (uint)ReadRegister(Reg + 0);
|
|
long High = (uint)ReadRegister(Reg + 1);
|
|
|
|
return Low | (High << 32);
|
|
}
|
|
|
|
private int ReadRegister(NvGpuEngine2dReg Reg)
|
|
{
|
|
return Registers[(int)Reg];
|
|
}
|
|
}
|
|
} |