OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

glsl: Add lowering pass for ir_triop_bitfield_extract

Browse Source 
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
This commit is contained in:
Ian Romanick
2016-06-23 16:57:23 -07:00
parent 7340be8a01
commit 4d6d219b58
2 changed files with 81 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/compiler/glsl/ir_optimization.h
View File

@@ -43,6 +43,7 @@
#define DOPS_TO_DFRAC 0x800
#define DFREXP_DLDEXP_TO_ARITH 0x1000
#define BIT_COUNT_TO_MATH 0x02000
#define EXTRACT_TO_SHIFTS 0x04000
/**
* \see class lower_packing_builtins_visitor

80
src/compiler/glsl/lower_instructions.cpp
View File

@@ -160,6 +160,7 @@ private:
void dtrunc_to_dfrac(ir_expression *);
void dsign_to_csel(ir_expression *);
void bit_count_to_math(ir_expression *);
void extract_to_shifts(ir_expression *);
};
} /* anonymous namespace */
@@ -1001,6 +1002,80 @@ lower_instructions_visitor::bit_count_to_math(ir_expression *ir)
this->progress = true;
}
void
lower_instructions_visitor::extract_to_shifts(ir_expression *ir)
{
ir_variable *bits =
new(ir) ir_variable(ir->operands[0]->type, "bits", ir_var_temporary);
base_ir->insert_before(bits);
base_ir->insert_before(assign(bits, ir->operands[2]));
if (ir->operands[0]->type->base_type == GLSL_TYPE_UINT) {
ir_constant *c1 =
new(ir) ir_constant(1u, ir->operands[0]->type->vector_elements);
ir_constant *c32 =
new(ir) ir_constant(32u, ir->operands[0]->type->vector_elements);
ir_constant *cFFFFFFFF =
new(ir) ir_constant(0xFFFFFFFFu, ir->operands[0]->type->vector_elements);
/* At least some hardware treats (x << y) as (x << (y%32)). This means
* we'd get a mask of 0 when bits is 32. Special case it.
*
* mask = bits == 32 ? 0xffffffff : (1u << bits) - 1u;
*/
ir_expression *mask = csel(equal(bits, c32),
cFFFFFFFF,
sub(lshift(c1, bits), c1->clone(ir, NULL)));
/* Section 8.8 (Integer Functions) of the GLSL 4.50 spec says:
*
* If bits is zero, the result will be zero.
*
* Since (1 << 0) - 1 == 0, we don't need to bother with the conditional
* select as in the signed integer case.
*
* (value >> offset) & mask;
*/
ir->operation = ir_binop_bit_and;
ir->operands[0] = rshift(ir->operands[0], ir->operands[1]);
ir->operands[1] = mask;
ir->operands[2] = NULL;
} else {
ir_constant *c0 =
new(ir) ir_constant(int(0), ir->operands[0]->type->vector_elements);
ir_constant *c32 =
new(ir) ir_constant(int(32), ir->operands[0]->type->vector_elements);
ir_variable *temp =
new(ir) ir_variable(ir->operands[0]->type, "temp", ir_var_temporary);
/* temp = 32 - bits; */
base_ir->insert_before(temp);
base_ir->insert_before(assign(temp, sub(c32, bits)));
/* expr = value << (temp - offset)) >> temp; */
ir_expression *expr =
rshift(lshift(ir->operands[0], sub(temp, ir->operands[1])), temp);
/* Section 8.8 (Integer Functions) of the GLSL 4.50 spec says:
*
* If bits is zero, the result will be zero.
*
* Due to the (x << (y%32)) behavior mentioned before, the (value <<
* (32-0)) doesn't "erase" all of the data as we would like, so finish
* up with:
*
* (bits == 0) ? 0 : e;
*/
ir->operation = ir_triop_csel;
ir->operands[0] = equal(c0, bits);
ir->operands[1] = c0->clone(ir, NULL);
ir->operands[2] = expr;
}
this->progress = true;
}
ir_visitor_status
lower_instructions_visitor::visit_leave(ir_expression *ir)
{
@@ -1108,6 +1183,11 @@ lower_instructions_visitor::visit_leave(ir_expression *ir)
bit_count_to_math(ir);
break;
case ir_triop_bitfield_extract:
if (lowering(EXTRACT_TO_SHIFTS))
extract_to_shifts(ir);
break;
default:
return visit_continue;
}