New shader translator implementation (#654)

* Start implementing a new shader translator

* Fix shift instructions and a typo

* Small refactoring on StructuredProgram, move RemovePhis method to a separate class

* Initial geometry shader support

* Implement TLD4

* Fix -- There's no negation on FMUL32I

* Add constant folding and algebraic simplification optimizations, nits

* Some leftovers from constant folding

* Avoid cast for constant assignments

* Add a branch elimination pass, and misc small fixes

* Remove redundant branches, add expression propagation and other improvements on the code

* Small leftovers -- add missing break and continue, remove unused properties, other improvements

* Add null check to handle empty block cases on block visitor

* Add HADD2 and HMUL2 half float shader instructions

* Optimize pack/unpack sequences, some fixes related to half float instructions

* Add TXQ, TLD, TLDS and TLD4S shader texture instructions, and some support for bindless textures, some refactoring on codegen

* Fix copy paste mistake that caused RZ to be ignored on the AST instruction

* Add workaround for conditional exit, and fix half float instruction with constant buffer

* Add missing 0.0 source for TLDS.LZ variants

* Simplify the switch for TLDS.LZ

* Texture instructions related fixes

* Implement the HFMA instruction, and some misc. fixes

* Enable constant folding on UnpackHalf2x16 instructions

* Refactor HFMA to use OpCode* for opcode decoding rather than on the helper methods

* Remove the old shader translator

* Remove ShaderDeclInfo and other unused things

* Add dual vertex shader support

* Add ShaderConfig, used to pass shader type and maximum cbuffer size

* Move and rename some instruction enums

* Move texture instructions into a separate file

* Move operand GetExpression and locals management to OperandManager

* Optimize opcode decoding using a simple list and binary search

* Add missing condition for do-while on goto elimination

* Misc. fixes on texture instructions

* Simplify TLDS switch

* Address PR feedback, and a nit

1 files changed, 14 insertions, 11 deletions

diff --git a/Ryujinx.Graphics/Graphics3d/NvGpuEngine3d.cs b/Ryujinx.Graphics/Graphics3d/NvGpuEngine3d.cs
index 605cbda8..bbed642b 100644
--- a/Ryujinx.Graphics/Graphics3d/NvGpuEngine3d.cs
+++ b/Ryujinx.Graphics/Graphics3d/NvGpuEngine3d.cs
@@ -1,6 +1,7 @@
 using Ryujinx.Common;
 using Ryujinx.Graphics.Gal;
 using Ryujinx.Graphics.Memory;
+using Ryujinx.Graphics.Shader;
 using Ryujinx.Graphics.Texture;
 using System;
 using System.Collections.Generic;
@@ -464,7 +465,7 @@ namespace Ryujinx.Graphics.Graphics3d
                         left  = _viewportX1 - (left  - _viewportX0);
                         right = _viewportX1 - (right - _viewportX0);
                     }
-                    
+
                     // Ensure X is in the right order
                     if (left > right)
                     {
@@ -626,20 +627,22 @@ namespace Ryujinx.Graphics.Graphics3d
 
             for (int index = 0; index < keys.Length; index++)
             {
-                foreach (ShaderDeclInfo declInfo in _gpu.Renderer.Shader.GetTextureUsage(keys[index]))
+                foreach (TextureDescriptor desc in _gpu.Renderer.Shader.GetTextureUsage(keys[index]))
                 {
-                    long position;
+                    int textureHandle;
 
-                    if (declInfo.IsCb)
+                    if (desc.IsBindless)
                     {
-                        position = _constBuffers[index][declInfo.Cbuf].Position;
+                        long position = _constBuffers[index][desc.CbufSlot].Position;
+
+                        textureHandle = vmm.ReadInt32(position + desc.CbufOffset * 4);
                     }
                     else
                     {
-                        position = _constBuffers[index][textureCbIndex].Position;
-                    }
+                        long position = _constBuffers[index][textureCbIndex].Position;
 
-                    int textureHandle = vmm.ReadInt32(position + declInfo.Index * 4);
+                        textureHandle = vmm.ReadInt32(position + desc.HandleIndex * 4);
+                    }
 
                     unboundTextures.Add(UploadTexture(vmm, textureHandle));
                 }
@@ -712,9 +715,9 @@ namespace Ryujinx.Graphics.Graphics3d
         {
             for (int stage = 0; stage < keys.Length; stage++)
             {
-                foreach (ShaderDeclInfo declInfo in _gpu.Renderer.Shader.GetConstBufferUsage(keys[stage]))
+                foreach (CBufferDescriptor desc in _gpu.Renderer.Shader.GetConstBufferUsage(keys[stage]))
                 {
-                    ConstBuffer cb = _constBuffers[stage][declInfo.Cbuf];
+                    ConstBuffer cb = _constBuffers[stage][desc.Slot];
 
                     if (!cb.Enabled)
                     {
@@ -735,7 +738,7 @@ namespace Ryujinx.Graphics.Graphics3d
                         }
                     }
 
-                    state.ConstBufferKeys[stage][declInfo.Cbuf] = key;
+                    state.ConstBufferKeys[stage][desc.Slot] = key;
                 }
             }
         }