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
2019-04-18 01:57:08 +02:00
|
|
|
using Ryujinx.Graphics.Shader.IntermediateRepresentation;
|
|
|
|
|
|
|
|
using static Ryujinx.Graphics.Shader.IntermediateRepresentation.OperandHelper;
|
|
|
|
|
|
|
|
namespace Ryujinx.Graphics.Shader.Translation.Optimizations
|
|
|
|
{
|
|
|
|
static class Simplification
|
|
|
|
{
|
|
|
|
private const int AllOnes = ~0;
|
|
|
|
|
2019-10-13 08:02:07 +02:00
|
|
|
public static void RunPass(Operation operation)
|
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
2019-04-18 01:57:08 +02:00
|
|
|
{
|
|
|
|
switch (operation.Inst)
|
|
|
|
{
|
|
|
|
case Instruction.Add:
|
|
|
|
case Instruction.BitwiseExclusiveOr:
|
2019-07-02 04:39:22 +02:00
|
|
|
TryEliminateBinaryOpCommutative(operation, 0);
|
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
2019-04-18 01:57:08 +02:00
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.BitwiseAnd:
|
|
|
|
TryEliminateBitwiseAnd(operation);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.BitwiseOr:
|
|
|
|
TryEliminateBitwiseOr(operation);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.ConditionalSelect:
|
|
|
|
TryEliminateConditionalSelect(operation);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.Divide:
|
|
|
|
TryEliminateBinaryOpY(operation, 1);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.Multiply:
|
2019-07-02 04:39:22 +02:00
|
|
|
TryEliminateBinaryOpCommutative(operation, 1);
|
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
2019-04-18 01:57:08 +02:00
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.ShiftLeft:
|
|
|
|
case Instruction.ShiftRightS32:
|
|
|
|
case Instruction.ShiftRightU32:
|
|
|
|
case Instruction.Subtract:
|
|
|
|
TryEliminateBinaryOpY(operation, 0);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void TryEliminateBitwiseAnd(Operation operation)
|
|
|
|
{
|
2019-07-02 04:39:22 +02:00
|
|
|
// Try to recognize and optimize those 3 patterns (in order):
|
|
|
|
// x & 0xFFFFFFFF == x, 0xFFFFFFFF & y == y,
|
|
|
|
// x & 0x00000000 == 0x00000000, 0x00000000 & y == 0x00000000
|
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
2019-04-18 01:57:08 +02:00
|
|
|
Operand x = operation.GetSource(0);
|
|
|
|
Operand y = operation.GetSource(1);
|
|
|
|
|
|
|
|
if (IsConstEqual(x, AllOnes))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(y);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(y, AllOnes))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(x);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(x, 0) || IsConstEqual(y, 0))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(Const(0));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void TryEliminateBitwiseOr(Operation operation)
|
|
|
|
{
|
2019-07-02 04:39:22 +02:00
|
|
|
// Try to recognize and optimize those 3 patterns (in order):
|
|
|
|
// x | 0x00000000 == x, 0x00000000 | y == y,
|
|
|
|
// x | 0xFFFFFFFF == 0xFFFFFFFF, 0xFFFFFFFF | y == 0xFFFFFFFF
|
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
2019-04-18 01:57:08 +02:00
|
|
|
Operand x = operation.GetSource(0);
|
|
|
|
Operand y = operation.GetSource(1);
|
|
|
|
|
|
|
|
if (IsConstEqual(x, 0))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(y);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(y, 0))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(x);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(x, AllOnes) || IsConstEqual(y, AllOnes))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(Const(AllOnes));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void TryEliminateBinaryOpY(Operation operation, int comparand)
|
|
|
|
{
|
|
|
|
Operand x = operation.GetSource(0);
|
|
|
|
Operand y = operation.GetSource(1);
|
|
|
|
|
|
|
|
if (IsConstEqual(y, comparand))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(x);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-07-02 04:39:22 +02:00
|
|
|
private static void TryEliminateBinaryOpCommutative(Operation operation, int comparand)
|
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
2019-04-18 01:57:08 +02:00
|
|
|
{
|
|
|
|
Operand x = operation.GetSource(0);
|
|
|
|
Operand y = operation.GetSource(1);
|
|
|
|
|
|
|
|
if (IsConstEqual(x, comparand))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(y);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(y, comparand))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(x);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void TryEliminateConditionalSelect(Operation operation)
|
|
|
|
{
|
|
|
|
Operand cond = operation.GetSource(0);
|
|
|
|
|
|
|
|
if (cond.Type != OperandType.Constant)
|
|
|
|
{
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2019-07-02 04:39:22 +02:00
|
|
|
// The condition is constant, we can turn it into a copy, and select
|
|
|
|
// the source based on the condition value.
|
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
2019-04-18 01:57:08 +02:00
|
|
|
int srcIndex = cond.Value != 0 ? 1 : 2;
|
|
|
|
|
|
|
|
Operand source = operation.GetSource(srcIndex);
|
|
|
|
|
|
|
|
operation.TurnIntoCopy(source);
|
|
|
|
}
|
|
|
|
|
|
|
|
private static bool IsConstEqual(Operand operand, int comparand)
|
|
|
|
{
|
|
|
|
if (operand.Type != OperandType.Constant)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
return operand.Value == comparand;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|