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
2019-04-17 16:57:08 -07:00
|
|
|
using Ryujinx.Graphics.Shader.IntermediateRepresentation;
|
|
|
|
using System;
|
|
|
|
|
|
|
|
namespace Ryujinx.Graphics.Shader.Translation.Optimizations
|
|
|
|
{
|
|
|
|
static class BranchElimination
|
|
|
|
{
|
2019-10-12 23:02:07 -07:00
|
|
|
public static bool RunPass(BasicBlock block)
|
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
2019-04-17 16:57:08 -07:00
|
|
|
{
|
|
|
|
if (block.HasBranch && IsRedundantBranch((Operation)block.GetLastOp(), Next(block)))
|
|
|
|
{
|
|
|
|
block.Branch = null;
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
private static bool IsRedundantBranch(Operation current, BasicBlock nextBlock)
|
|
|
|
{
|
2019-07-01 19:39:22 -07:00
|
|
|
// Here we check that:
|
|
|
|
// - The current block ends with a branch.
|
|
|
|
// - The next block only contains a branch.
|
|
|
|
// - The branch on the next block is unconditional.
|
|
|
|
// - Both branches are jumping to the same location.
|
|
|
|
// In this case, the branch on the current block can be removed,
|
|
|
|
// as the next block is going to jump to the same place anyway.
|
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
2019-04-17 16:57:08 -07:00
|
|
|
if (nextBlock == null)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!(nextBlock.Operations.First?.Value is Operation next))
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (next.Inst != Instruction.Branch)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
return current.Dest == next.Dest;
|
|
|
|
}
|
|
|
|
|
|
|
|
private static BasicBlock Next(BasicBlock block)
|
|
|
|
{
|
|
|
|
block = block.Next;
|
|
|
|
|
|
|
|
while (block != null && block.Operations.Count == 0)
|
|
|
|
{
|
|
|
|
if (block.HasBranch)
|
|
|
|
{
|
|
|
|
throw new InvalidOperationException("Found a bogus empty block that \"ends with a branch\".");
|
|
|
|
}
|
|
|
|
|
|
|
|
block = block.Next;
|
|
|
|
}
|
|
|
|
|
|
|
|
return block;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|