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:
Takoroka 2026-10-27 22:26:16 -04:00
commit 9bee875c48

View file

@ -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;
}