Switch 2: Turing macros, native compute, Ampere shader lowering, native tiling
From changes.patch: the TU104/GA10x MME interpreter (shared macro context for the process's channels, also on the compute class), native compute with QMD 3.0 dependency scheduling, the Ampere-to-Maxwell shader lowering, native vertex stream sizes, and the console's GOB swizzle for textures, DMA copies and the host unswizzle shaders. Switch 2 channels turn all of it on at init. The lowering is widened for title 4 (all 32 of its programs lower): general TEX (any dimension/LOD/mask, operand split 1+1/2+1/2+2/4+n, any but consistent descriptor buffer), cube/array, SULD channel masks, 128-bit STG, indexed IPA, VOTE, SHFL with any immediate or predicate output, R2P/P2R byte select, uniform ULOP3/ULEA/UBREV/UFLO.SH/UISETP signed/UMOV URZ, IMNMX cbuf, IADD3 and FFMA uniform operands, FMUL /4 /8 x8, and BSSY/BSYNC/BREAK/WARPSYNC as no-ops. The capture stops at unmapped memory. EDEN_NX2_SHADER_DUMP dumps every native program; tools in C:\dev\nx2work test the lowering offline.
This commit is contained in:
parent
09630c34ed
commit
9bee875c48
1 changed files with 2930 additions and 69 deletions
|
|
@ -439,7 +439,7 @@ template <u32 GOB_EXTENT>
|
|||
}
|
||||
layers = 1;
|
||||
} else {
|
||||
layers = (std::max)(resources.layers, info.resources.layers + base->layer);
|
||||
layers = (std::max)(info.resources.layers, resources.layers + base->layer);
|
||||
}
|
||||
return OverlapResult{
|
||||
.gpu_addr = overlap.gpu_addr,
|
||||
|
|
@ -566,7 +566,7 @@ void SwizzleBlockLinearImage(Tegra::MemoryManager& gpu_memory, GPUVAddr gpu_addr
|
|||
dst(gpu_memory, gpu_addr + guest_offset, subresource_size, &tmp_buffer);
|
||||
|
||||
SwizzleTexture(dst, src, bytes_per_block, num_tiles.width, num_tiles.height,
|
||||
num_tiles.depth, block.height, block.depth);
|
||||
num_tiles.depth, block.height, block.depth, 1, gpu_memory.UsesNativeTiling());
|
||||
}
|
||||
|
||||
host_offset += host_bytes_per_layer;
|
||||
|
|
@ -913,7 +913,7 @@ boost::container::small_vector<BufferImageCopy, 16> UnswizzleImage(Tegra::Memory
|
|||
const std::span<u8> dst = output.subspan(host_offset);
|
||||
const std::span<const u8> src = input.subspan(guest_offset + guest_layer_offset);
|
||||
UnswizzleTexture(dst, src, 1U << bpp_log2, num_tiles.width, num_tiles.height,
|
||||
num_tiles.depth, block.height, block.depth, stride_alignment);
|
||||
num_tiles.depth, block.height, block.depth, stride_alignment, gpu_memory.UsesNativeTiling());
|
||||
guest_layer_offset += layer_stride;
|
||||
host_offset += host_bytes_per_layer;
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in a new issue