From: Francisco Casas fcasas@codeweavers.com
For temporary registers, SM1-SM3 integer types are internally represented as floating point, so, in order to perform a cast from ints to floats we need a mere MOV.
For constant integer registers "iN" there is no operation for casting from a floating point register to them. For address registers "aN", and the loop counting register "aL", vertex shaders have the "mova" operation but we haven't used these registers in any way yet.
We probably would want to introduce these as synthetic variables allocated in a special register set. In that case we have to remember to use MOVA instead of MOV in the store operations, but they shouldn't be src or dst of CAST operations.
Regarding constant integer registers, in some shaders, constants are expected to be received formatted as an integer, such as:
int m; float4 main() : sv_target { float4 res = {0, 0, 0, 0};
for (int k = 0; k < m; ++k) res += k; return res; }
which compiles as:
// Registers: // // Name Reg Size // ------------ ----- ---- // m i0 1 //
ps_3_0 def c0, 0, 1, 0, 0 mov r0, c0.x mov r1.x, c0.x rep i0 add r0, r0, r1.x add r1.x, r1.x, c0.y endrep mov oC0, r0
but this only happens if the integer constant is used directly in an instruction that needs it, and as I said there is no instruction that allows converting them to a float representation.
Notice how a more complex shader, that performs operations with this integer variable "m":
int m; float4 main() : sv_target { float4 res = {0, 0, 0, 0};
for (int k = 0; k < m * m; ++k) res += k; return res; }
gives the following output:
// Registers: // // Name Reg Size // ------------ ----- ---- // m c0 1 //
ps_3_0 def c1, 0, 0, 1, 0 defi i0, 255, 0, 0, 0 mul r0.x, c0.x, c0.x mov r1, c1.y mov r0.y, c1.y rep i0 mov r0.z, r0.x break_ge r0.y, r0.z add r1, r0.y, r1 add r0.y, r0.y, c1.z endrep mov oC0, r1
Meaning that the uniform "m" is just stored as a floating point in "c0", the constant integer register "i0" is just set to 255 (hoping it is a high enough value) using "defi", and the "break_ge" involving c0 is used to break from the loop.
We could potentially use this approach to implement loops from SM3 without expecting the variables being received as constant integer registers.
According to the D3D documentation, for SM1-SM3 constant integer registers are only used by the 'loop' and 'rep' instructions. --- libs/vkd3d-shader/d3dbc.c | 82 +++++++++++++++++++++++++++++++++ tests/hlsl/distance.shader_test | 2 +- tests/hlsl/half.shader_test | 4 +- tests/hlsl/ldexp.shader_test | 4 +- tests/hlsl/lerp.shader_test | 4 +- 5 files changed, 89 insertions(+), 7 deletions(-)
diff --git a/libs/vkd3d-shader/d3dbc.c b/libs/vkd3d-shader/d3dbc.c index 4ba001ea4..69fe6db89 100644 --- a/libs/vkd3d-shader/d3dbc.c +++ b/libs/vkd3d-shader/d3dbc.c @@ -1957,6 +1957,84 @@ static void write_sm1_unary_op(struct hlsl_ctx *ctx, struct vkd3d_bytecode_buffe write_sm1_instruction(ctx, buffer, &instr); }
+static void write_sm1_cast(struct hlsl_ctx *ctx, struct vkd3d_bytecode_buffer *buffer, + const struct hlsl_ir_node *instr) +{ + struct hlsl_ir_expr *expr = hlsl_ir_expr(instr); + const struct hlsl_ir_node *arg1 = expr->operands[0].node; + const struct hlsl_type *dst_type = expr->node.data_type; + const struct hlsl_type *src_type = arg1->data_type; + + /* Narrowing casts were already lowered. */ + assert(src_type->dimx == dst_type->dimx); + + switch (dst_type->base_type) + { + case HLSL_TYPE_HALF: + case HLSL_TYPE_FLOAT: + switch (src_type->base_type) + { + case HLSL_TYPE_INT: + case HLSL_TYPE_UINT: + /* Integers are internally represented as floats, so no change is necessary.*/ + case HLSL_TYPE_HALF: + case HLSL_TYPE_FLOAT: + write_sm1_unary_op(ctx, buffer, D3DSIO_MOV, &instr->reg, &arg1->reg, 0, 0); + break; + + case HLSL_TYPE_BOOL: + hlsl_fixme(ctx, &instr->loc, "SM1 cast from bool to float."); + break; + + case HLSL_TYPE_DOUBLE: + hlsl_fixme(ctx, &instr->loc, "SM1 cast from double to float."); + break; + + default: + vkd3d_unreachable(); + } + break; + + case HLSL_TYPE_INT: + case HLSL_TYPE_UINT: + switch(src_type->base_type) + { + case HLSL_TYPE_INT: + case HLSL_TYPE_UINT: + write_sm1_unary_op(ctx, buffer, D3DSIO_MOV, &instr->reg, &arg1->reg, 0, 0); + break; + + case HLSL_TYPE_HALF: + case HLSL_TYPE_FLOAT: + hlsl_fixme(ctx, &instr->loc, "SM1 cast from float to integer."); + break; + + case HLSL_TYPE_BOOL: + hlsl_fixme(ctx, &instr->loc, "SM1 cast from bool to integer."); + break; + + case HLSL_TYPE_DOUBLE: + hlsl_fixme(ctx, &instr->loc, "SM1 cast from double to integer."); + break; + + default: + vkd3d_unreachable(); + } + break; + + case HLSL_TYPE_DOUBLE: + hlsl_fixme(ctx, &instr->loc, "SM1 cast to double."); + break; + + case HLSL_TYPE_BOOL: + /* Casts to bool should have already been lowered. */ + default: + hlsl_fixme(ctx, &expr->node.loc, "SM1 cast from %s to %s.\n", + debug_hlsl_type(ctx, src_type), debug_hlsl_type(ctx, dst_type)); + break; + } +} + static void write_sm1_constant_defs(struct hlsl_ctx *ctx, struct vkd3d_bytecode_buffer *buffer) { unsigned int i, x; @@ -2178,6 +2256,10 @@ static void write_sm1_expr(struct hlsl_ctx *ctx, struct vkd3d_bytecode_buffer *b write_sm1_unary_op(ctx, buffer, D3DSIO_ABS, &instr->reg, &arg1->reg, 0, 0); break;
+ case HLSL_OP1_CAST: + write_sm1_cast(ctx, buffer, instr); + break; + case HLSL_OP1_DSX: write_sm1_unary_op(ctx, buffer, D3DSIO_DSX, &instr->reg, &arg1->reg, 0, 0); break; diff --git a/tests/hlsl/distance.shader_test b/tests/hlsl/distance.shader_test index bf2423c7a..3f5446451 100644 --- a/tests/hlsl/distance.shader_test +++ b/tests/hlsl/distance.shader_test @@ -13,7 +13,7 @@ uniform 4 float4 2.0 -1.0 4.0 5.0 draw quad probe all rgba (7.483983, 7.483983, 7.483983, 7.483983) 1
-[pixel shader todo(sm<4)] +[pixel shader] uniform int4 x; uniform int4 y;
diff --git a/tests/hlsl/half.shader_test b/tests/hlsl/half.shader_test index 8cf7a756f..fe7074e45 100644 --- a/tests/hlsl/half.shader_test +++ b/tests/hlsl/half.shader_test @@ -9,7 +9,7 @@ float4 main() : sv_target [require] options: backcompat
-[pixel shader todo(sm<4)] +[pixel shader] uniform half h;
float4 main() : sv_target @@ -19,5 +19,5 @@ float4 main() : sv_target
[test] uniform 0 float 10.0 -todo(sm<4) draw quad +draw quad probe all rgba (10.0, 10.0, 10.0, 10.0) diff --git a/tests/hlsl/ldexp.shader_test b/tests/hlsl/ldexp.shader_test index 3becf5f60..d7275d0c5 100644 --- a/tests/hlsl/ldexp.shader_test +++ b/tests/hlsl/ldexp.shader_test @@ -14,7 +14,7 @@ draw quad probe all rgba (2.0, 0.00292968750, 4096.0, 6.33825300e+030) 2
-[pixel shader todo(sm<4)] +[pixel shader] uniform int4 x; uniform int4 y;
@@ -26,7 +26,7 @@ float4 main() : SV_TARGET [test] uniform 0 int4 2 3 4 5 uniform 4 int4 0 -10 10 100 -todo(sm<4) draw quad +draw quad probe all rgba (2.0, 0.00292968750, 4096.0, 6.33825300e+030) 2
diff --git a/tests/hlsl/lerp.shader_test b/tests/hlsl/lerp.shader_test index e3dbc1e89..23921adc1 100644 --- a/tests/hlsl/lerp.shader_test +++ b/tests/hlsl/lerp.shader_test @@ -16,7 +16,7 @@ draw quad probe all rgba (2.0, -10.0, -2.0, 76.25)
-[pixel shader todo(sm<4)] +[pixel shader] uniform int4 x; uniform int4 y; uniform int4 s; @@ -30,7 +30,7 @@ float4 main() : SV_TARGET uniform 0 int4 2 3 4 0 uniform 4 int4 0 -10 10 1000000 uniform 8 int4 0 1 -1 1000000 -todo(sm<4) draw quad +draw quad probe all rgba (2.0, -10.0, -2.0, 1e12)