[PATCH v3 0/8] MR744: vkd3d-shader/hlsl: Improve SM1 support for non-float operations, part 5.
-- v3: vkd3d-shader/hlsl: Use LOGIC_AND instead of MUL in all(). vkd3d-shader/hlsl: Use LOGIC_OR instead of BIT_OR in any(). vkd3d-shader/ir: Add missing src swizzle in vsir_program_lower_texkills(). tests: Add failing test for clip.shader_test in SM1. vkd3d-shader/tpf: Use the extra_bits field for _nz on discard. tests: Report missing signature element in openGL runner. vkd3d-shader/hlsl: Move lower of non-float expressions with the other SM1 passes. vkd3d-shader/hlsl: Ensure that TERNARY condition is always bool.
From: Francisco Casas fcasas@codeweavers.com
Also, properly casting it to float in lower_ternary() for SM1 avoids creating ABS and NEG on bool types. --- libs/vkd3d-shader/hlsl.h | 10 ++-- libs/vkd3d-shader/hlsl.y | 51 ++++++++++++------- libs/vkd3d-shader/hlsl_codegen.c | 42 ++++++++------- libs/vkd3d-shader/hlsl_constant_ops.c | 23 +-------- .../hlsl/arithmetic-float-uniform.shader_test | 16 +++--- tests/hlsl/float-comparison.shader_test | 4 +- tests/hlsl/fmod.shader_test | 12 ++--- tests/hlsl/inverse-trig.shader_test | 44 ++++++++-------- tests/hlsl/lit.shader_test | 12 ++--- tests/hlsl/ternary.shader_test | 18 +++---- tests/hlsl/vertex-shader-ops.shader_test | 6 +-- 11 files changed, 115 insertions(+), 123 deletions(-)
diff --git a/libs/vkd3d-shader/hlsl.h b/libs/vkd3d-shader/hlsl.h index 64111f3fc..4f3501014 100644 --- a/libs/vkd3d-shader/hlsl.h +++ b/libs/vkd3d-shader/hlsl.h @@ -600,12 +600,10 @@ enum hlsl_ir_expr_op /* DP2ADD(a, b, c) computes the scalar product of a.xy and b.xy, * then adds c. */ HLSL_OP3_DP2ADD, - /* MOVC(a, b, c) returns c if a is bitwise zero and b otherwise. - * TERNARY(a, b, c) returns c if a == 0 and b otherwise. - * They differ for floating point numbers, because - * -0.0 == 0.0, but it is not bitwise zero. CMP(a, b, c) returns b - if a >= 0, and c otherwise. It's used only for SM1-SM3 targets, while - SM4+ is using MOVC in such cases. */ + /* TERNARY(a, b, c) returns 'b' if 'a' is true and 'b' otherwise. 'a' must always be boolean. + * MOVC(a, b, c) returns 'c' if 'a' is bitwise zero and 'b' otherwise. + * CMP(a, b, c) returns 'b' if 'a' >= 0, and 'c' otherwise. It's used only for SM1-SM3 targets, + while SM4+ is using MOVC in such cases. */ HLSL_OP3_CMP, HLSL_OP3_MOVC, HLSL_OP3_TERNARY, diff --git a/libs/vkd3d-shader/hlsl.y b/libs/vkd3d-shader/hlsl.y index 52c217654..4fcc5b54f 100644 --- a/libs/vkd3d-shader/hlsl.y +++ b/libs/vkd3d-shader/hlsl.y @@ -4413,26 +4413,34 @@ static bool add_ternary(struct hlsl_ctx *ctx, struct hlsl_block *block, if (!(cond = add_implicit_conversion(ctx, block, cond, cond_type, &cond->loc))) return false; } - else if (common_type->dimx == 1 && common_type->dimy == 1) - { - common_type = hlsl_get_numeric_type(ctx, cond_type->class, - common_type->base_type, cond_type->dimx, cond_type->dimy); - } - else if (cond_type->dimx != common_type->dimx || cond_type->dimy != common_type->dimy) + else { - /* This condition looks wrong but is correct. - * floatN is compatible with float1xN, but not with floatNx1. */ - - struct vkd3d_string_buffer *cond_string, *value_string; + cond_type = hlsl_get_numeric_type(ctx, cond_type->class, HLSL_TYPE_BOOL, + cond_type->dimx, cond_type->dimy); + if (!(cond = add_implicit_conversion(ctx, block, cond, cond_type, &cond->loc))) + return false;
- cond_string = hlsl_type_to_string(ctx, cond_type); - value_string = hlsl_type_to_string(ctx, common_type); - if (cond_string && value_string) - hlsl_error(ctx, &first->loc, VKD3D_SHADER_ERROR_HLSL_INVALID_TYPE, - "Ternary condition type '%s' is not compatible with value type '%s'.", - cond_string->buffer, value_string->buffer); - hlsl_release_string_buffer(ctx, cond_string); - hlsl_release_string_buffer(ctx, value_string); + if (common_type->dimx == 1 && common_type->dimy == 1) + { + common_type = hlsl_get_numeric_type(ctx, cond_type->class, + common_type->base_type, cond_type->dimx, cond_type->dimy); + } + else if (cond_type->dimx != common_type->dimx || cond_type->dimy != common_type->dimy) + { + /* This condition looks wrong but is correct. + * floatN is compatible with float1xN, but not with floatNx1. */ + + struct vkd3d_string_buffer *cond_string, *value_string; + + cond_string = hlsl_type_to_string(ctx, cond_type); + value_string = hlsl_type_to_string(ctx, common_type); + if (cond_string && value_string) + hlsl_error(ctx, &first->loc, VKD3D_SHADER_ERROR_HLSL_INVALID_TYPE, + "Ternary condition type '%s' is not compatible with value type '%s'.", + cond_string->buffer, value_string->buffer); + hlsl_release_string_buffer(ctx, cond_string); + hlsl_release_string_buffer(ctx, value_string); + } }
if (!(first = add_implicit_conversion(ctx, block, first, common_type, &first->loc))) @@ -4457,9 +4465,16 @@ static bool add_ternary(struct hlsl_ctx *ctx, struct hlsl_block *block, hlsl_release_string_buffer(ctx, second_string); }
+ cond_type = hlsl_get_numeric_type(ctx, cond_type->class, HLSL_TYPE_BOOL, + cond_type->dimx, cond_type->dimy); + if (!(cond = add_implicit_conversion(ctx, block, cond, cond_type, &cond->loc))) + return false; + common_type = first->data_type; }
+ assert(cond->data_type->base_type == HLSL_TYPE_BOOL); + args[0] = cond; args[1] = first; args[2] = second; diff --git a/libs/vkd3d-shader/hlsl_codegen.c b/libs/vkd3d-shader/hlsl_codegen.c index 5c09ce04f..2f3b7ce0d 100644 --- a/libs/vkd3d-shader/hlsl_codegen.c +++ b/libs/vkd3d-shader/hlsl_codegen.c @@ -2955,8 +2955,7 @@ static bool lower_logic_not(struct hlsl_ctx *ctx, struct hlsl_ir_node *instr, st static bool lower_ternary(struct hlsl_ctx *ctx, struct hlsl_ir_node *instr, struct hlsl_block *block) { struct hlsl_ir_node *operands[HLSL_MAX_OPERANDS] = { 0 }, *replacement; - struct hlsl_ir_node *zero, *cond, *first, *second; - struct hlsl_constant_value zero_value = { 0 }; + struct hlsl_ir_node *cond, *first, *second, *float_cond, *neg; struct hlsl_ir_expr *expr; struct hlsl_type *type;
@@ -2977,18 +2976,22 @@ static bool lower_ternary(struct hlsl_ctx *ctx, struct hlsl_ir_node *instr, stru return false; }
+ assert(cond->data_type->base_type == HLSL_TYPE_BOOL); + if (ctx->profile->major_version < 4) { - struct hlsl_ir_node *abs, *neg; + type = hlsl_get_numeric_type(ctx, instr->data_type->class, HLSL_TYPE_FLOAT, + instr->data_type->dimx, instr->data_type->dimy);
- if (!(abs = hlsl_new_unary_expr(ctx, HLSL_OP1_ABS, cond, &instr->loc))) + if (!(float_cond = hlsl_new_cast(ctx, cond, type, &instr->loc))) return false; - hlsl_block_add_instr(block, abs); + hlsl_block_add_instr(block, float_cond);
- if (!(neg = hlsl_new_unary_expr(ctx, HLSL_OP1_NEG, abs, &instr->loc))) + if (!(neg = hlsl_new_unary_expr(ctx, HLSL_OP1_NEG, float_cond, &instr->loc))) return false; hlsl_block_add_instr(block, neg);
+ memset(operands, 0, sizeof(operands)); operands[0] = neg; operands[1] = second; operands[2] = first; @@ -2997,21 +3000,6 @@ static bool lower_ternary(struct hlsl_ctx *ctx, struct hlsl_ir_node *instr, stru } else { - if (cond->data_type->base_type == HLSL_TYPE_FLOAT) - { - if (!(zero = hlsl_new_constant(ctx, cond->data_type, &zero_value, &instr->loc))) - return false; - hlsl_block_add_instr(block, zero); - - operands[0] = zero; - operands[1] = cond; - type = cond->data_type; - type = hlsl_get_numeric_type(ctx, type->class, HLSL_TYPE_BOOL, type->dimx, type->dimy); - if (!(cond = hlsl_new_expr(ctx, HLSL_OP2_NEQUAL, operands, type, &instr->loc))) - return false; - hlsl_block_add_instr(block, cond); - } - memset(operands, 0, sizeof(operands)); operands[0] = cond; operands[1] = first; @@ -3316,11 +3304,21 @@ static bool lower_casts_to_bool(struct hlsl_ctx *ctx, struct hlsl_ir_node *instr struct hlsl_ir_node *hlsl_add_conditional(struct hlsl_ctx *ctx, struct hlsl_block *instrs, struct hlsl_ir_node *condition, struct hlsl_ir_node *if_true, struct hlsl_ir_node *if_false) { + struct hlsl_type *cond_type = condition->data_type; struct hlsl_ir_node *operands[HLSL_MAX_OPERANDS]; struct hlsl_ir_node *cond;
assert(hlsl_types_are_equal(if_true->data_type, if_false->data_type));
+ if (cond_type->base_type != HLSL_TYPE_BOOL) + { + cond_type = hlsl_get_numeric_type(ctx, cond_type->class, HLSL_TYPE_BOOL, cond_type->dimx, cond_type->dimy); + + if (!(condition = hlsl_new_cast(ctx, condition, cond_type, &condition->loc))) + return NULL; + hlsl_block_add_instr(instrs, condition); + } + operands[0] = condition; operands[1] = if_true; operands[2] = if_false; @@ -5419,11 +5417,11 @@ int hlsl_emit_bytecode(struct hlsl_ctx *ctx, struct hlsl_ir_function_decl *entry hlsl_transform_ir(ctx, split_matrix_copies, body, NULL);
lower_ir(ctx, lower_narrowing_casts, body); - lower_ir(ctx, lower_casts_to_bool, body); lower_ir(ctx, lower_int_dot, body); lower_ir(ctx, lower_int_division, body); lower_ir(ctx, lower_int_modulus, body); lower_ir(ctx, lower_int_abs, body); + lower_ir(ctx, lower_casts_to_bool, body); lower_ir(ctx, lower_float_modulus, body); hlsl_transform_ir(ctx, fold_redundant_casts, body, NULL); do diff --git a/libs/vkd3d-shader/hlsl_constant_ops.c b/libs/vkd3d-shader/hlsl_constant_ops.c index b76b1fce5..4cea98e92 100644 --- a/libs/vkd3d-shader/hlsl_constant_ops.c +++ b/libs/vkd3d-shader/hlsl_constant_ops.c @@ -1177,30 +1177,11 @@ static bool fold_ternary(struct hlsl_ctx *ctx, struct hlsl_constant_value *dst,
assert(dst_type->base_type == src2->node.data_type->base_type); assert(dst_type->base_type == src3->node.data_type->base_type); + assert(src1->node.data_type->base_type == HLSL_TYPE_BOOL);
for (k = 0; k < dst_type->dimx; ++k) - { - switch (src1->node.data_type->base_type) - { - case HLSL_TYPE_FLOAT: - case HLSL_TYPE_HALF: - dst->u[k] = src1->value.u[k].f != 0.0f ? src2->value.u[k] : src3->value.u[k]; - break; - - case HLSL_TYPE_DOUBLE: - dst->u[k] = src1->value.u[k].d != 0.0 ? src2->value.u[k] : src3->value.u[k]; - break; + dst->u[k] = src1->value.u[k].u ? src2->value.u[k] : src3->value.u[k];
- case HLSL_TYPE_INT: - case HLSL_TYPE_UINT: - case HLSL_TYPE_BOOL: - dst->u[k] = src1->value.u[k].u ? src2->value.u[k] : src3->value.u[k]; - break; - - default: - vkd3d_unreachable(); - } - } return true; }
diff --git a/tests/hlsl/arithmetic-float-uniform.shader_test b/tests/hlsl/arithmetic-float-uniform.shader_test index 8bc3992e7..61957f2bb 100644 --- a/tests/hlsl/arithmetic-float-uniform.shader_test +++ b/tests/hlsl/arithmetic-float-uniform.shader_test @@ -13,7 +13,7 @@ uniform 0 float4 5.0 15.0 0.0 0.0 todo(glsl) draw quad probe all rgba (20.0, -10.0, 75.0, 0.33333333) 1
-[pixel shader todo(sm<4)] +[pixel shader] uniform float2 a;
float4 main() : SV_TARGET @@ -25,10 +25,10 @@ float4 main() : SV_TARGET
[test] uniform 0 float4 5.0 15.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (5.0, 5.0, -5.0, 3.0) 1
-[pixel shader todo(sm<4)] +[pixel shader] uniform float2 a;
float4 main() : SV_TARGET @@ -40,10 +40,10 @@ float4 main() : SV_TARGET
[test] uniform 0 float4 42.0 5.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (2.0, -2.0, 2.0, -2.0) 16
-[pixel shader todo(sm<4)] +[pixel shader] uniform float2 a;
float4 main() : SV_TARGET @@ -55,10 +55,10 @@ float4 main() : SV_TARGET
[test] uniform 0 float4 45.0 5.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.0, 0.0, 0.0, 0.0)
-[pixel shader todo(sm<4)] +[pixel shader] float4 x, y;
float4 main() : sv_target @@ -69,7 +69,7 @@ float4 main() : sv_target [test] uniform 0 float4 5.0 -42.1 4.0 45.0 uniform 4 float4 15.0 -5.0 4.1 5.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (5.0, -2.1, 4.0, 0.0) 6
[require] diff --git a/tests/hlsl/float-comparison.shader_test b/tests/hlsl/float-comparison.shader_test index 84c09c129..56ce46f36 100644 --- a/tests/hlsl/float-comparison.shader_test +++ b/tests/hlsl/float-comparison.shader_test @@ -13,7 +13,7 @@ todo(glsl) draw quad probe all rgba (0.0, 0.0, 0.0, 0.0)
-[pixel shader todo(sm<4)] +[pixel shader] uniform float4 f;
float4 main() : sv_target @@ -55,7 +55,7 @@ float4 main() : sv_target
[test] uniform 0 float4 0.0 1.5 1.5 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad % SM1-3 apparently treats '0/0' as zero. if(sm<4) todo probe all rgba (1010101.0, 11001100.0, 1101001.0, 11.0) % SM4-5 optimises away the 'not' by inverting the condition, even though this is invalid for NaN. diff --git a/tests/hlsl/fmod.shader_test b/tests/hlsl/fmod.shader_test index ccb7b99e7..40dc66e8c 100644 --- a/tests/hlsl/fmod.shader_test +++ b/tests/hlsl/fmod.shader_test @@ -1,4 +1,4 @@ -[pixel shader todo(sm<4)] +[pixel shader] uniform float4 u;
float4 main() : sv_target @@ -8,13 +8,13 @@ float4 main() : sv_target
[test] uniform 0 float4 -0.5 6.5 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (-0.5, 0.0, 0.0, 0.0) 4 uniform 0 float4 1.1 0.3 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.2, 0.0, 0.0, 0.0) 4
-[pixel shader todo(sm<4)] +[pixel shader] uniform float4 u;
float4 main() : sv_target @@ -24,8 +24,8 @@ float4 main() : sv_target
[test] uniform 0 float4 -0.5 6.5 2.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (-0.5, 0.5, 0.0, 0.0) 4 uniform 0 float4 1.1 0.3 3.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.1, 0.3, 0.0, 0.0) 4 diff --git a/tests/hlsl/inverse-trig.shader_test b/tests/hlsl/inverse-trig.shader_test index 31af0ceef..62d79e9ff 100644 --- a/tests/hlsl/inverse-trig.shader_test +++ b/tests/hlsl/inverse-trig.shader_test @@ -92,7 +92,7 @@ todo(glsl) draw quad probe all rgba (31416.0, 0.0, 0.0, 0.0)
-[pixel shader todo(sm<4)] +[pixel shader] uniform float4 a;
float4 main() : sv_target @@ -102,26 +102,26 @@ float4 main() : sv_target
[test] uniform 0 float4 -1.0 0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (-0.785409629, 0.0, 0.0, 0.0) 512
uniform 0 float4 -0.5 0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (-0.4636476, 0.0, 0.0, 0.0) 256
uniform 0 float4 0.0 0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.0, 0.0, 0.0, 0.0) 256
uniform 0 float4 0.5 0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.4636476, 0.0, 0.0, 0.0) 256
uniform 0 float4 1.0 0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.785409629, 0.0, 0.0, 0.0) 512
-[pixel shader todo(sm<4)] +[pixel shader] uniform float4 a;
float4 main() : sv_target @@ -133,64 +133,64 @@ float4 main() : sv_target [test] % Non-degenerate cases uniform 0 float4 1.0 1.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.785385, 0.0, 0.0, 0.0) 512
uniform 0 float4 5.0 -5.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (2.356194, 0.0, 0.0, 0.0) 256
uniform 0 float4 -3.0 -3.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (-2.356194, 0.0, 0.0, 0.0) 256
uniform 0 float4 1.0 0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.570796, 0.0, 0.0, 0.0) 256
uniform 0 float4 -1.0 0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (-1.570796, 0.0, 0.0, 0.0) 256
uniform 0 float4 0.0 1.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.0, 0.0, 0.0, 0.0) 256
uniform 0 float4 0.0 -1.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (3.1415927, 0.0, 0.0, 0.0) 256
% Degenerate cases uniform 0 float4 0.00001 0.00002 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.463647, 0.0, 0.0, 0.0) 256
uniform 0 float4 0.00001 -0.00002 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (2.677945, 0.0, 0.0, 0.0) 256
uniform 0 float4 -0.00001 100000.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (-0.000000000099986595, 0.0, 0.0, 0.0) 2048
uniform 0 float4 10000000.0 0.00000001 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.570796, 0.0, 0.0, 0.0) 256
% Negative zero behavior should be to treat it the % same as normal zero. uniform 0 float4 1000000000.0 0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.570796, 0.0, 0.0, 0.0) 256
uniform 0 float4 1000000000.0 -0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.570796, 0.0, 0.0, 0.0) 256
uniform 0 float4 0.0 -1.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (3.1415927, 0.0, 0.0, 0.0) 256
uniform 0 float4 -0.0 -1.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (3.1415927, 0.0, 0.0, 0.0) 256 diff --git a/tests/hlsl/lit.shader_test b/tests/hlsl/lit.shader_test index efb249dba..ce68d6ea9 100644 --- a/tests/hlsl/lit.shader_test +++ b/tests/hlsl/lit.shader_test @@ -1,4 +1,4 @@ -[pixel shader todo(sm<4)] +[pixel shader] uniform float4 u;
float4 main() : sv_target @@ -8,20 +8,20 @@ float4 main() : sv_target
[test] uniform 0 float4 -0.1 10.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 0.0, 0.0, 1.0)
[test] uniform 0 float4 1.2 -0.1 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.2, 0.0, 1.0)
[test] uniform 0 float4 1.2 2.0 3.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.2, 8.0, 1.0)
-[pixel shader todo(sm<4)] +[pixel shader] uniform float4 u;
float4 main() : sv_target @@ -31,7 +31,7 @@ float4 main() : sv_target
[test] uniform 0 float4 1.2 2.0 3.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (2.0, 2.4, 16.0, 2.0)
[pixel shader fail] diff --git a/tests/hlsl/ternary.shader_test b/tests/hlsl/ternary.shader_test index c075b1e5a..91802afd4 100644 --- a/tests/hlsl/ternary.shader_test +++ b/tests/hlsl/ternary.shader_test @@ -3,7 +3,7 @@ shader model < 6.0
-[pixel shader todo(sm<4)] +[pixel shader] uniform float4 x;
float4 main() : sv_target @@ -13,14 +13,14 @@ float4 main() : sv_target
[test] uniform 0 float4 2.0 3.0 4.0 5.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (2.0, 3.0, 4.0, 5.0) uniform 0 float4 0.0 10.0 11.0 12.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (-1.0, 9.0, 10.0, 11.0)
-[pixel shader todo(sm<4)] +[pixel shader] uniform float4 x;
float4 main() : sv_target @@ -35,11 +35,11 @@ float4 main() : sv_target
[test] uniform 0 float4 1.1 3.0 4.0 5.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.1, 2.0, 0.0, 0.0)
-[pixel shader todo(sm<4)] +[pixel shader] float4 f;
float4 main() : sv_target @@ -51,7 +51,7 @@ float4 main() : sv_target
[test] uniform 0 float4 1.0 0.0 0.0 0.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.5, 0.6, 0.7, 0.0)
@@ -246,7 +246,7 @@ todo(glsl) draw quad probe all rgba (3.0, 3.0, 3.0, 3.0)
-[pixel shader todo(sm<4)] +[pixel shader]
uniform float cond; uniform float4 a, b; @@ -260,7 +260,7 @@ float4 main() : sv_target uniform 0 float4 1.0 0.0 0.0 0.0 uniform 4 float4 1.0 2.0 3.0 4.0 uniform 8 float4 5.0 6.0 7.0 8.0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 2.0, 3.0, 4.0)
diff --git a/tests/hlsl/vertex-shader-ops.shader_test b/tests/hlsl/vertex-shader-ops.shader_test index ee2a72f02..ea2a3df81 100644 --- a/tests/hlsl/vertex-shader-ops.shader_test +++ b/tests/hlsl/vertex-shader-ops.shader_test @@ -88,7 +88,7 @@ probe all rgba (1.0, 1.0, 1.0, 1.0) % The ternary operator works differently in sm6. See sm6-ternary.shader_test. shader model < 6.0
-[vertex shader todo(sm<4)] +[vertex shader] int a, b, c;
void main(out float4 res : COLOR1, in float4 pos : position, out float4 out_pos : sv_position) @@ -103,11 +103,11 @@ if(sm<4) uniform 0 float 0 if(sm<4) uniform 4 float 100 if(sm<4) uniform 8 float 200 if(sm>=4) uniform 0 int4 0 100 200 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.2, 0.2, 0.2, 0.2) if(sm<4) uniform 0 float -4 if(sm<4) uniform 4 float 100 if(sm<4) uniform 8 float 200 if(sm>=4) uniform 0 int4 -4 100 200 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.1, 0.1, 0.1, 0.1)
From: Francisco Casas fcasas@codeweavers.com
--- libs/vkd3d-shader/hlsl_codegen.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/libs/vkd3d-shader/hlsl_codegen.c b/libs/vkd3d-shader/hlsl_codegen.c index 2f3b7ce0d..1b13ec23b 100644 --- a/libs/vkd3d-shader/hlsl_codegen.c +++ b/libs/vkd3d-shader/hlsl_codegen.c @@ -5437,13 +5437,6 @@ int hlsl_emit_bytecode(struct hlsl_ctx *ctx, struct hlsl_ir_function_decl *entry remove_unreachable_code(ctx, body); hlsl_transform_ir(ctx, normalize_switch_cases, body, NULL);
- if (profile-> major_version < 4) - { - lower_ir(ctx, lower_nonfloat_exprs, body); - /* Constants casted to float must be folded. */ - hlsl_transform_ir(ctx, hlsl_fold_constant_exprs, body, NULL); - } - lower_ir(ctx, lower_nonconstant_vector_derefs, body); lower_ir(ctx, lower_casts_to_bool, body); lower_ir(ctx, lower_int_dot, body); @@ -5458,6 +5451,11 @@ int hlsl_emit_bytecode(struct hlsl_ctx *ctx, struct hlsl_ir_function_decl *entry lower_ir(ctx, lower_ternary, body); if (profile->major_version < 4) { + lower_ir(ctx, lower_nonfloat_exprs, body); + /* Constants casted to float must be folded, and new casts to bool also need to be lowered. */ + hlsl_transform_ir(ctx, hlsl_fold_constant_exprs, body, NULL); + lower_ir(ctx, lower_casts_to_bool, body); + lower_ir(ctx, lower_casts_to_int, body); lower_ir(ctx, lower_division, body); lower_ir(ctx, lower_sqrt, body);
From: Francisco Casas fcasas@codeweavers.com
--- tests/shader_runner_gl.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/tests/shader_runner_gl.c b/tests/shader_runner_gl.c index 3c2a41965..cbcfd95bb 100644 --- a/tests/shader_runner_gl.c +++ b/tests/shader_runner_gl.c @@ -1043,6 +1043,7 @@ static bool gl_runner_draw(struct shader_runner *r,
signature_element = vkd3d_shader_find_signature_element(&vs_input_signature, element->name, element->index, 0); + ok(signature_element, "Cannot find signature element %s%u.\n", element->name, element->index); attribute_idx = signature_element->register_index; format = get_format_info(element->format, false);
From: Francisco Casas fcasas@codeweavers.com
--- libs/vkd3d-shader/tpf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/libs/vkd3d-shader/tpf.c b/libs/vkd3d-shader/tpf.c index 4d0658313..5c25f262b 100644 --- a/libs/vkd3d-shader/tpf.c +++ b/libs/vkd3d-shader/tpf.c @@ -5399,7 +5399,8 @@ static void write_sm4_jump(const struct tpf_writer *tpf, const struct hlsl_ir_ju
case HLSL_IR_JUMP_DISCARD_NZ: { - instr.opcode = VKD3D_SM4_OP_DISCARD | VKD3D_SM4_CONDITIONAL_NZ; + instr.opcode = VKD3D_SM4_OP_DISCARD; + instr.extra_bits = VKD3D_SM4_CONDITIONAL_NZ;
memset(&instr.srcs[0], 0, sizeof(*instr.srcs)); instr.src_count = 1;
From: Francisco Casas fcasas@codeweavers.com
We are not properly translating texkill to spir-v since it is only considering the first component. --- tests/hlsl/clip.shader_test | 6 ++++++ 1 file changed, 6 insertions(+)
diff --git a/tests/hlsl/clip.shader_test b/tests/hlsl/clip.shader_test index 1ebc06871..64ccb6b12 100644 --- a/tests/hlsl/clip.shader_test +++ b/tests/hlsl/clip.shader_test @@ -20,3 +20,9 @@ probe all rgba (9, 8, 7, 6) uniform 0 float4 9 0 7 6 todo(glsl) draw quad probe all rgba (9, 0, 7, 6) +uniform 0 float4 3 -8 3 0 +todo(glsl) draw quad +todo(sm<4) probe all rgba (9, 0, 7, 6) +uniform 0 float4 3 3 3 -1 +todo(glsl) draw quad +todo(sm<4) probe all rgba (9, 0, 7, 6)
From: Francisco Casas fcasas@codeweavers.com
--- libs/vkd3d-shader/ir.c | 1 + tests/hlsl/clip.shader_test | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/libs/vkd3d-shader/ir.c b/libs/vkd3d-shader/ir.c index 4f0226187..3a1b58a7c 100644 --- a/libs/vkd3d-shader/ir.c +++ b/libs/vkd3d-shader/ir.c @@ -127,6 +127,7 @@ static enum vkd3d_result vsir_program_lower_texkills(struct vsir_program *progra ins->dst[0].write_mask = VKD3DSP_WRITEMASK_ALL;
ins->src[0].reg = texkill_ins->dst[0].reg; + ins->src[0].swizzle = VKD3D_SHADER_SWIZZLE(X, Y, Z, W); vsir_register_init(&ins->src[1].reg, VKD3DSPR_IMMCONST, VKD3D_DATA_FLOAT, 0); ins->src[1].reg.dimension = VSIR_DIMENSION_VEC4; ins->src[1].reg.u.immconst_f32[0] = 0.0f; diff --git a/tests/hlsl/clip.shader_test b/tests/hlsl/clip.shader_test index 64ccb6b12..4a8d223ca 100644 --- a/tests/hlsl/clip.shader_test +++ b/tests/hlsl/clip.shader_test @@ -22,7 +22,7 @@ todo(glsl) draw quad probe all rgba (9, 0, 7, 6) uniform 0 float4 3 -8 3 0 todo(glsl) draw quad -todo(sm<4) probe all rgba (9, 0, 7, 6) +probe all rgba (9, 0, 7, 6) uniform 0 float4 3 3 3 -1 todo(glsl) draw quad -todo(sm<4) probe all rgba (9, 0, 7, 6) +probe all rgba (9, 0, 7, 6)
From: Francisco Casas fcasas@codeweavers.com
Note that BIT_OR is not available for SM1 bools, so we must prefer LOGIC_OR when possible. --- libs/vkd3d-shader/hlsl.y | 68 ++++++++++++++------------------------ tests/hlsl/any.shader_test | 20 +++++------ 2 files changed, 34 insertions(+), 54 deletions(-)
diff --git a/libs/vkd3d-shader/hlsl.y b/libs/vkd3d-shader/hlsl.y index 4fcc5b54f..fb0d11862 100644 --- a/libs/vkd3d-shader/hlsl.y +++ b/libs/vkd3d-shader/hlsl.y @@ -2721,6 +2721,14 @@ static bool intrinsic_acos(struct hlsl_ctx *ctx, return write_acos_or_asin(ctx, params, loc, false); }
+/* Find the type corresponding to the given source type, with the same + * dimensions but a different base type. */ +static struct hlsl_type *convert_numeric_type(const struct hlsl_ctx *ctx, + const struct hlsl_type *type, enum hlsl_base_type base_type) +{ + return hlsl_get_numeric_type(ctx, type->class, base_type, type->dimx, type->dimy); +} + static bool intrinsic_all(struct hlsl_ctx *ctx, const struct parse_initializer *params, const struct vkd3d_shader_location *loc) { @@ -2750,52 +2758,33 @@ static bool intrinsic_all(struct hlsl_ctx *ctx, return !!add_binary_comparison_expr(ctx, params->instrs, HLSL_OP2_NEQUAL, mul, zero, loc); }
-static bool intrinsic_any(struct hlsl_ctx *ctx, - const struct parse_initializer *params, const struct vkd3d_shader_location *loc) +static bool intrinsic_any(struct hlsl_ctx *ctx, const struct parse_initializer *params, + const struct vkd3d_shader_location *loc) { - struct hlsl_ir_node *arg = params->args[0], *dot, *or, *zero, *bfalse, *load; + struct hlsl_ir_node *arg = params->args[0], *or, *load, *cast; + struct hlsl_type *bool_type; unsigned int i, count;
- if (arg->data_type->class != HLSL_CLASS_VECTOR && arg->data_type->class != HLSL_CLASS_SCALAR) - { - hlsl_fixme(ctx, loc, "any() implementation for non-vector, non-scalar"); - return false; - } + count = hlsl_type_component_count(arg->data_type); + bool_type = convert_numeric_type(ctx, arg->data_type, HLSL_TYPE_BOOL);
- if (arg->data_type->base_type == HLSL_TYPE_FLOAT) - { - if (!(zero = hlsl_new_float_constant(ctx, 0.0f, loc))) - return false; - hlsl_block_add_instr(params->instrs, zero); + if (!(cast = add_cast(ctx, params->instrs, arg, bool_type, loc))) + return false;
- if (!(dot = add_binary_dot_expr(ctx, params->instrs, arg, arg, loc))) - return false; + if (!(or = hlsl_add_load_component(ctx, params->instrs, cast, 0, loc))) + return false;
- return !!add_binary_comparison_expr(ctx, params->instrs, HLSL_OP2_NEQUAL, dot, zero, loc); - } - else if (arg->data_type->base_type == HLSL_TYPE_BOOL) + for (i = 1; i < count; ++i) { - if (!(bfalse = hlsl_new_bool_constant(ctx, false, loc))) + if (!(load = hlsl_add_load_component(ctx, params->instrs, cast, i, loc))) return false; - hlsl_block_add_instr(params->instrs, bfalse);
- or = bfalse; - - count = hlsl_type_component_count(arg->data_type); - for (i = 0; i < count; ++i) - { - if (!(load = hlsl_add_load_component(ctx, params->instrs, arg, i, loc))) - return false; - - if (!(or = add_binary_bitwise_expr(ctx, params->instrs, HLSL_OP2_BIT_OR, or, load, loc))) - return false; - } - - return true; + if (!(or = hlsl_new_binary_expr(ctx, HLSL_OP2_LOGIC_OR, or, load))) + return NULL; + hlsl_block_add_instr(params->instrs, or); }
- hlsl_fixme(ctx, loc, "any() implementation for non-float, non-bool"); - return false; + return true; }
static bool intrinsic_asin(struct hlsl_ctx *ctx, @@ -2896,15 +2885,6 @@ static bool intrinsic_atan2(struct hlsl_ctx *ctx, return write_atan_or_atan2(ctx, params, loc, true); }
- -/* Find the type corresponding to the given source type, with the same - * dimensions but a different base type. */ -static struct hlsl_type *convert_numeric_type(const struct hlsl_ctx *ctx, - const struct hlsl_type *type, enum hlsl_base_type base_type) -{ - return hlsl_get_numeric_type(ctx, type->class, base_type, type->dimx, type->dimy); -} - static bool intrinsic_asfloat(struct hlsl_ctx *ctx, const struct parse_initializer *params, const struct vkd3d_shader_location *loc) { diff --git a/tests/hlsl/any.shader_test b/tests/hlsl/any.shader_test index b143dd414..8a7408286 100644 --- a/tests/hlsl/any.shader_test +++ b/tests/hlsl/any.shader_test @@ -49,7 +49,7 @@ todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0)
-[pixel shader todo(sm<4)] +[pixel shader] uniform uint4 b;
float4 main() : sv_target @@ -60,30 +60,30 @@ float4 main() : sv_target [test] if(sm<4) uniform 0 float4 1 1 1 1 if(sm>=4) uniform 0 uint4 1 1 1 1 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 1 0 0 0 if(sm>=4) uniform 0 uint4 1 0 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 1 0 0 if(sm>=4) uniform 0 uint4 0 1 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 0 1 0 if(sm>=4) uniform 0 uint4 0 0 1 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 0 0 1 if(sm>=4) uniform 0 uint4 0 0 0 1 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 0 0 0 if(sm>=4) uniform 0 uint4 0 0 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.0, 0.0, 0.0, 0.0)
-[pixel shader todo(sm<4)] +[pixel shader] uniform uint b;
float4 main() : sv_target @@ -94,9 +94,9 @@ float4 main() : sv_target [test] if(sm<4) uniform 0 float4 1 0 0 0 if(sm>=4) uniform 0 uint4 1 0 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 0 0 0 if(sm>=4) uniform 0 uint4 0 0 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.0, 0.0, 0.0, 0.0)
From: Francisco Casas fcasas@codeweavers.com
--- libs/vkd3d-shader/hlsl.y | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/libs/vkd3d-shader/hlsl.y b/libs/vkd3d-shader/hlsl.y index fb0d11862..6a674630a 100644 --- a/libs/vkd3d-shader/hlsl.y +++ b/libs/vkd3d-shader/hlsl.y @@ -2732,30 +2732,30 @@ static struct hlsl_type *convert_numeric_type(const struct hlsl_ctx *ctx, static bool intrinsic_all(struct hlsl_ctx *ctx, const struct parse_initializer *params, const struct vkd3d_shader_location *loc) { - struct hlsl_ir_node *arg = params->args[0], *mul, *one, *zero, *load; + struct hlsl_ir_node *arg = params->args[0], *and, *load, *cast; + struct hlsl_type *bool_type; unsigned int i, count;
- if (!(one = hlsl_new_float_constant(ctx, 1.0f, loc))) - return false; - hlsl_block_add_instr(params->instrs, one); + count = hlsl_type_component_count(arg->data_type); + bool_type = convert_numeric_type(ctx, arg->data_type, HLSL_TYPE_BOOL);
- if (!(zero = hlsl_new_float_constant(ctx, 0.0f, loc))) + if (!(cast = add_cast(ctx, params->instrs, arg, bool_type, loc))) return false; - hlsl_block_add_instr(params->instrs, zero);
- mul = one; + if (!(and = hlsl_add_load_component(ctx, params->instrs, cast, 0, loc))) + return false;
- count = hlsl_type_component_count(arg->data_type); - for (i = 0; i < count; ++i) + for (i = 1; i < count; ++i) { - if (!(load = hlsl_add_load_component(ctx, params->instrs, arg, i, loc))) + if (!(load = hlsl_add_load_component(ctx, params->instrs, cast, i, loc))) return false;
- if (!(mul = add_binary_arithmetic_expr(ctx, params->instrs, HLSL_OP2_MUL, load, mul, loc))) - return false; + if (!(and = hlsl_new_binary_expr(ctx, HLSL_OP2_LOGIC_AND, and, load))) + return NULL; + hlsl_block_add_instr(params->instrs, and); }
- return !!add_binary_comparison_expr(ctx, params->instrs, HLSL_OP2_NEQUAL, mul, zero, loc); + return true; }
static bool intrinsic_any(struct hlsl_ctx *ctx, const struct parse_initializer *params,
:arrow_up: For now, replaced the previous solution to the missing float casts in the lower_ternary() with patch 1/8. Also added 2/8 because it is a step towards moving backend-specific passes to latter in the code.
Giovanni Mascellani (@giomasce) commented about libs/vkd3d-shader/hlsl.h:
/* DP2ADD(a, b, c) computes the scalar product of a.xy and b.xy, * then adds c. */ HLSL_OP3_DP2ADD,
- /* MOVC(a, b, c) returns c if a is bitwise zero and b otherwise.
* TERNARY(a, b, c) returns c if a == 0 and b otherwise.* They differ for floating point numbers, because* -0.0 == 0.0, but it is not bitwise zero. CMP(a, b, c) returns bif a >= 0, and c otherwise. It's used only for SM1-SM3 targets, whileSM4+ is using MOVC in such cases. */
- /* TERNARY(a, b, c) returns 'b' if 'a' is true and 'b' otherwise. 'a' must always be boolean.
`'c' otherwise`, I believe.
However, it seems that TERNARY is now a subcase of MOVC. Is there a reason for not merging them?
Giovanni Mascellani (@giomasce) commented about libs/vkd3d-shader/ir.c:
ins->dst[0].write_mask = VKD3DSP_WRITEMASK_ALL; ins->src[0].reg = texkill_ins->dst[0].reg;
ins->src[0].swizzle = VKD3D_SHADER_SWIZZLE(X, Y, Z, W);
Not a big deal, but notice we also have `VKD3D_SHADER_NO_SWIZZLE`. The name doesn't feel entirely correct to me, but it does the same thing.
Giovanni Mascellani (@giomasce) commented about libs/vkd3d-shader/hlsl.y:
static bool intrinsic_all(struct hlsl_ctx *ctx, const struct parse_initializer *params, const struct vkd3d_shader_location *loc)
That's fine for me, but notice that if you want you can refactor `all()` and `any()` to a common helper that takes the accumulation operation as a parameter.
This merge request was approved by Giovanni Mascellani.
This merge request was approved by Zebediah Figura.
-
Francisco Casas -
Francisco Casas (＠fcasas)
-
Giovanni Mascellani (＠giomasce)
-
Zebediah Figura (＠zfigura)