GS rasterizer rework (#132)

* [runtime] Memory swizzling rework

Reimplementation of memory swizzling supporting all valid GS texture
storage types.

An additional optimization was done to improve the speed of lookups.
Since page access is linear, we can precompute the non-linear bit
(blocks and columns) for an entire page for each format. This reduces
the runtime calculation to just calculating the correct page in 2d
memory space and then performing a lookup in the table to get the
location in memory inside a page. Since all page accesses are the same,
this works across all pages. Speed improvements should be compounded by
the number of accesses but there might be some reductions as a result of
actually implementing formats that were not implemented before.

I took care to do this with simple math. GS swizzling is complicated and
optimizing it for debug builds is outside the scope of my current work.

This is just the standalone code. It will be worked into the current
rasterizer in a follow up commit.

* [runtime] Reimplement GS host -> local transfers

Reimplement the host -> local transfers using new swizzling code

* [runtime] Reimplement sampling with new swizzling

Reimplements the rasterizer sampling code to use the new swizzling code

* [runtime] Replace fb writes with new swizzling

Replace the framebuffer write code with the new swizzling code

* [runtime] Reduce vram read/write to func lookup

Reduces the vram read write switches to a function lookup

* [tests] fix GS tests not handling depth test

* [runtime] z interpolation and write support

Add support for interpolating z from primitives and writing to the z
buffer after z testing and masking

* [runtime] local to local transfer rework

* [runtime] host readout uses new sizzling code

plus cleanup some dead code

* [runtime] rework local->host transfer

update to the new swizzling code

* [runtime] update clear function with new swizzling

Author: tealalchemist

ps2xRuntime/CMakeLists.txt

@@ -167,6 +167,7 @@ add_library(ps2_runtime STATIC
     src/lib/ps2_audio.cpp
     src/lib/ps2_audio_vag.cpp
     src/lib/ps2_gs_gpu.cpp
+    src/lib/ps2_gs_memory.cpp
     src/lib/ps2_gs_rasterizer.cpp
     src/lib/ps2_iop.cpp
     src/lib/ps2_iop_audio.cpp

ps2xRuntime/include/runtime/ps2_gs_gpu.h

@@ -1,12 +1,15 @@
 #ifndef PS2_GS_GPU_H
 #define PS2_GS_GPU_H
 
-#include "ps2_gs_rasterizer.h"
+#include <functional>
 #include <cstdint>
 #include <cstring>
 #include <mutex>
 #include <vector>
 
+#include "ps2_gs_rasterizer.h"
+#include "ps2_gs_memory.h"
+
 enum GSPrimType : uint8_t
 {
     GS_PRIM_POINT = 0,
@@ -105,7 +108,9 @@ enum GSRegId : uint8_t
 
 struct GSVertex
 {
-    float x, y, z;
+    float x, y;
+    // double because float isnt accurate enough for values near UINT32_MAX
+    double z;
     uint8_t r, g, b, a;
     float q;
     float s, t;
@@ -121,6 +126,13 @@ struct GSFrameReg
     uint32_t fbmsk;
 };
 
+struct GSZbufReg
+{
+    u32 zbp;
+    u8 psm;
+    bool zmask;
+};
+
 struct GSScissorReg
 {
     uint16_t x0, x1, y0, y1;
@@ -168,7 +180,7 @@ struct GSContext
     GSScissorReg scissor;
     GSTex0Reg tex0;
     GSXYOffsetReg xyoffset;
-    uint64_t zbuf;
+    GSZbufReg zbuf;
     uint64_t tex1;
     uint64_t clamp;
     uint64_t alpha;
@@ -249,6 +261,9 @@ class GS
 
     void refreshDisplaySnapshot();
 
+    inline void WriteVram(u32 psm, uint32_t base, uint32_t bw, uint32_t x, uint32_t y, uint32_t value);
+    inline u32 ReadVram(u32 psm, u32 base, u32 bw, u32 x, u32 y) const;
+
 private:
     void snapshotVRAM();
     void writeRegisterPacked(uint8_t regDesc, uint64_t lo, uint64_t hi);
@@ -292,8 +307,14 @@ class GS
     GSTrxPos m_trxpos{};
     GSTrxReg m_trxreg{};
     uint32_t m_trxdir = 3;
-    uint32_t m_hwregX = 0;
-    uint32_t m_hwregY = 0;
+
+    struct
+    {
+        uint32_t x{ 0 };
+        uint32_t y{ 0 };
+        uint32_t total_pixels{ 0 };
+        uint32_t copied_pixels{ 0 };
+    } m_transferState;
 
     static constexpr int kMaxVerts = 6;
     GSVertex m_vtxQueue[kMaxVerts];
@@ -318,6 +339,22 @@ class GS
     size_t m_localToHostReadPos = 0;
 
     GSRasterizer m_rasterizer;
+
+    using WriteVramFunc = std::function<void(u8*, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t)>;
+    using ReadVramFunc = std::function<u32(u8*, u32, u32, u32, u32)>;
+
+    std::array<ReadVramFunc, 0x3F> m_read_vram_funcs{ };
+    std::array<WriteVramFunc, 0x3F> m_write_vram_funcs{ };
 };
 
+inline u32 GS::ReadVram(u32 psm, u32 base, u32 bw, u32 x, u32 y) const
+{
+    return m_read_vram_funcs[psm & 0x3F](m_vram, base, bw, x, y);
+}
+
+inline void GS::WriteVram(u32 psm, u32 base, u32 bw, u32 x, u32 y, u32 value)
+{
+    m_write_vram_funcs[psm & 0x3F](m_vram, base, bw, x, y, value);
+}
+
 #endif