Merge pull request #931 from LoopDawg/scalar-mat-assign

Test/baseResults/hlsl.intrinsics.negative.frag.out

 hlsl.intrinsics.negative.frag
-ERROR: 0:10: 'determinant' : no matching overloaded function found 
+ERROR: 0:10: 'determinant' : ambiguous best function under implicit type conversion 
 ERROR: 0:25: 'normalize' : ambiguous best function under implicit type conversion 
 ERROR: 0:26: 'reflect' : ambiguous best function under implicit type conversion 
 ERROR: 0:27: 'refract' : ambiguous best function under implicit type conversion 
 ERROR: 0:28: 'refract' : no matching overloaded function found 
-ERROR: 0:30: 'transpose' : no matching overloaded function found 
+ERROR: 0:30: 'transpose' : ambiguous best function under implicit type conversion 
 ERROR: 0:39: 'GetRenderTargetSamplePosition' : no matching overloaded function found 
 ERROR: 0:46: 'asdouble' : double2 conversion not implemented 
 ERROR: 0:47: 'CheckAccessFullyMapped' : no matching overloaded function found 
@@ -104,8 +104,9 @@ ERROR: node is still EOpNull!
 0:9                0 (const int)
 0:9              Constant:
 0:9                3 (const int)
-0:10      Constant:
-0:10        0.000000
+0:10      determinant ( temp float)
+ERROR: node is still EOpNull!
+0:10          'inF0' ( in float)
 0:12      direct index ( temp float)
 0:12        unpackHalf2x16 ( temp 2-component vector of float)
 0:12          Convert float to uint ( temp uint)
@@ -150,8 +151,9 @@ ERROR: node is still EOpNull!
 0:29      bitFieldReverse ( temp uint)
 0:29        Convert float to uint ( temp uint)
 0:29          'inF0' ( in float)
-0:30      Constant:
-0:30        0.000000
+0:30      transpose ( temp 1X1 matrix of float)
+ERROR: node is still EOpNull!
+0:30          'inF0' ( in float)
 0:32      Branch: Return with expression
 0:32        Constant:
 0:32          0.000000
@@ -565,8 +567,9 @@ ERROR: node is still EOpNull!
 0:9                0 (const int)
 0:9              Constant:
 0:9                3 (const int)
-0:10      Constant:
-0:10        0.000000
+0:10      determinant ( temp float)
+ERROR: node is still EOpNull!
+0:10          'inF0' ( in float)
 0:12      direct index ( temp float)
 0:12        unpackHalf2x16 ( temp 2-component vector of float)
 0:12          Convert float to uint ( temp uint)
@@ -611,8 +614,9 @@ ERROR: node is still EOpNull!
 0:29      bitFieldReverse ( temp uint)
 0:29        Convert float to uint ( temp uint)
 0:29          'inF0' ( in float)
-0:30      Constant:
-0:30        0.000000
+0:30      transpose ( temp 1X1 matrix of float)
+ERROR: node is still EOpNull!
+0:30          'inF0' ( in float)
 0:32      Branch: Return with expression
 0:32        Constant:
 0:32          0.000000

Test/baseResults/hlsl.type.half.frag.out

@@ -49,11 +49,11 @@ gl_FragCoord origin is upper left
 0:16          'h23' ( temp 2X3 matrix of float)
 0:16          Constant:
 0:16            4.900000
-0:16            0.000000
-0:16            0.000000
-0:16            0.000000
 0:16            4.900000
-0:16            0.000000
+0:16            4.900000
+0:16            4.900000
+0:16            4.900000
+0:16            4.900000
 0:27      Branch: Return with expression
 0:27        Construct vec4 ( temp 4-component vector of float)
 0:27          add ( temp float)
@@ -133,11 +133,11 @@ gl_FragCoord origin is upper left
 0:16          'h23' ( temp 2X3 matrix of float)
 0:16          Constant:
 0:16            4.900000
-0:16            0.000000
-0:16            0.000000
-0:16            0.000000
 0:16            4.900000
-0:16            0.000000
+0:16            4.900000
+0:16            4.900000
+0:16            4.900000
+0:16            4.900000
 0:27      Branch: Return with expression
 0:27        Construct vec4 ( temp 4-component vector of float)
 0:27          add ( temp float)
@@ -165,12 +165,12 @@ gl_FragCoord origin is upper left
 
 // Module Version 10000
 // Generated by (magic number): 80001
-// Id's are bound by 61
+// Id's are bound by 60
 
                               Capability Shader
                1:             ExtInstImport  "GLSL.std.450"
                               MemoryModel Logical GLSL450
-                              EntryPoint Fragment 4  "main" 59
+                              EntryPoint Fragment 4  "main" 58
                               ExecutionMode 4 OriginUpperLeft
                               Source HLSL 500
                               Name 4  "main"
@@ -182,8 +182,8 @@ gl_FragCoord origin is upper left
                               Name 27  "h4"
                               Name 32  "h22"
                               Name 38  "h23"
-                              Name 59  "@entryPointOutput"
-                              Decorate 59(@entryPointOutput) Location 0
+                              Name 58  "@entryPointOutput"
+                              Decorate 58(@entryPointOutput) Location 0
                2:             TypeVoid
                3:             TypeFunction 2
                6:             TypeFloat 32
@@ -211,20 +211,19 @@ gl_FragCoord origin is upper left
               36:             TypeMatrix 21(fvec3) 2
               37:             TypePointer Function 36
               39:    6(float) Constant 1084017869
-              40:   21(fvec3) ConstantComposite 39 13 13
-              41:   21(fvec3) ConstantComposite 13 39 13
-              42:          36 ConstantComposite 40 41
-              43:             TypeInt 32 1
-              44:     43(int) Constant 0
-              45:             TypeInt 32 0
-              46:     45(int) Constant 0
-              49:     45(int) Constant 1
-              58:             TypePointer Output 7(fvec4)
-59(@entryPointOutput):     58(ptr) Variable Output
+              40:   21(fvec3) ConstantComposite 39 39 39
+              41:          36 ConstantComposite 40 40
+              42:             TypeInt 32 1
+              43:     42(int) Constant 0
+              44:             TypeInt 32 0
+              45:     44(int) Constant 0
+              48:     44(int) Constant 1
+              57:             TypePointer Output 7(fvec4)
+58(@entryPointOutput):     57(ptr) Variable Output
          4(main):           2 Function None 3
                5:             Label
-              60:    7(fvec4) FunctionCall 9(@main()
-                              Store 59(@entryPointOutput) 60
+              59:    7(fvec4) FunctionCall 9(@main()
+                              Store 58(@entryPointOutput) 59
                               Return
                               FunctionEnd
        9(@main():    7(fvec4) Function None 8
@@ -242,14 +241,14 @@ gl_FragCoord origin is upper left
                               Store 23(h3) 25
                               Store 27(h4) 29
                               Store 32(h22) 35
-                              Store 38(h23) 42
-              47:     11(ptr) AccessChain 38(h23) 44 46
-              48:    6(float) Load 47
-              50:     11(ptr) AccessChain 27(h4) 49
-              51:    6(float) Load 50
-              52:    6(float) FAdd 48 51
-              53:    6(float) Load 12(h0)
-              54:    6(float) FAdd 52 53
-              55:    7(fvec4) CompositeConstruct 54 54 54 54
-                              ReturnValue 55
+                              Store 38(h23) 41
+              46:     11(ptr) AccessChain 38(h23) 43 45
+              47:    6(float) Load 46
+              49:     11(ptr) AccessChain 27(h4) 48
+              50:    6(float) Load 49
+              51:    6(float) FAdd 47 50
+              52:    6(float) Load 12(h0)
+              53:    6(float) FAdd 51 52
+              54:    7(fvec4) CompositeConstruct 53 53 53 53
+                              ReturnValue 54
                               FunctionEnd

Test/hlsl.scalar2matrix.frag

+
+void Fn1(float4x4 p) { }
+
+float4 main() : SV_TARGET
+{
+    const float4x4 mat1c = 0.20;
+    const float4x4 mat2c = {2, 2.1, 2.2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+    const float4x4 mat3c = (float4x4)float1(0.1);
+
+    float4x4 mat1 = 0.25;
+    float4x4 mat2 = {3, 3.1, 3.2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+    float4x4 mat3 = (float4x4)0.375;
+    // float4x4 mat5 = (float4x4)Fn2(); // TODO: enable when compex rvalue handling is in place
+
+    float4x4 mat4;
+    mat4 = 0.75;
+    mat4 = float4x4(4, 4.1, 4.2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
+    mat4 = (float4x4)0.5;
+
+    mat4 *= 0.75;
+    mat4 += 0.75;
+    mat4 -= 0.5;
+    mat4 /= 2.0;
+
+    Fn1(5.0); // test calling fn accepting matrix with scalar type
+
+    return mat1c[0] + mat3c[0] + mat1[1] + mat4[2];
+}

glslang/MachineIndependent/Intermediate.cpp

@@ -1043,6 +1043,32 @@ TIntermTyped* TIntermediate::addShapeConversion(const TType& type, TIntermTyped*
     // The new node that handles the conversion
     TOperator constructorOp = mapTypeToConstructorOp(type);
 
+    // HLSL has custom semantics for scalar->mat shape conversions.
+    if (source == EShSourceHlsl) {
+        if (node->getType().isScalarOrVec1() && type.isMatrix()) {
+
+            // HLSL semantics: the scalar (or vec1) is replicated to every component of the matrix.  Left to its
+            // own devices, the constructor from a scalar would populate the diagonal.  This forces replication
+            // to every matrix element.
+
+            // Note that if the node is complex (e.g, a function call), we don't want to duplicate it here
+            // repeatedly, so we copy it to a temp, then use the temp.
+            const int matSize = type.getMatrixRows() * type.getMatrixCols();
+            TIntermAggregate* rhsAggregate = new TIntermAggregate();
+
+            const bool isSimple = (node->getAsSymbolNode() != nullptr) || (node->getAsConstantUnion() != nullptr);
+
+            if (!isSimple) {
+                assert(0); // TODO: use node replicator service when available.
+            }
+            
+            for (int x=0; x<matSize; ++x)
+                rhsAggregate->getSequence().push_back(node);
+
+            return setAggregateOperator(rhsAggregate, constructorOp, type, node->getLoc());
+        }
+    }
+
     // scalar -> vector or vec1 -> vector or
     // vector -> scalar or
     // bigger vector -> smaller vector

gtests/Hlsl.FromFile.cpp

@@ -285,6 +285,7 @@ INSTANTIATE_TEST_CASE_P(
         {"hlsl.max.frag", "PixelShaderFunction"},
         {"hlsl.precedence.frag", "PixelShaderFunction"},
         {"hlsl.precedence2.frag", "PixelShaderFunction"},
+        {"hlsl.scalar2matrix.frag", "main"},
         {"hlsl.semantic.geom", "main"},
         {"hlsl.semantic.vert", "main"},
         {"hlsl.scope.frag", "PixelShaderFunction"},

hlsl/hlslParseHelper.cpp

@@ -6616,6 +6616,7 @@ const TFunction* HlslParseContext::findFunction(const TSourceLoc& loc, TFunction
         // shapes have to be convertible
         if ((from.isScalarOrVec1() && to.isScalarOrVec1()) ||
             (from.isScalarOrVec1() && to.isVector())    ||
+            (from.isScalarOrVec1() && to.isMatrix())    ||
             (from.isVector() && to.isVector() && from.getVectorSize() >= to.getVectorSize()))
             return true;
 
@@ -7393,8 +7394,15 @@ TIntermTyped* HlslParseContext::addConstructor(const TSourceLoc& loc, TIntermTyp
             newNode = constructAggregate(node, elementType, 1, node->getLoc());
         else if (op == EOpConstructStruct)
             newNode = constructAggregate(node, *(*memberTypes).type, 1, node->getLoc());
-        else
+        else {
+            // shape conversion for matrix constructor from scalar.  HLSL semantics are: scalar
+            // is replicated into every element of the matrix (not just the diagnonal), so
+            // that is handled specially here.
+            if (type.isMatrix() && node->getType().isScalarOrVec1())
+                node = intermediate.addShapeConversion(type, node);
+
             newNode = constructBuiltIn(type, op, node, node->getLoc(), false);
+        }
 
         if (newNode && (type.isArray() || op == EOpConstructStruct))
             newNode = intermediate.setAggregateOperator(newNode, EOpConstructStruct, type, loc);