nir/constant_expressions: Rework Boolean handling

This commit contains three related changes.  First, we define boolN_t
for N = 8, 16, and 64 and move the definition of boolN_vec to the loop
with the other vec definitions.  Second, there's no reason why we need
the != 0 on the source because that happens implicitly when it's
converted to bool.  Third, for destinations, we use a signed integer
type and just do -(int)bool_val which will give us the 0/-1 behavior we
want and neatly scales to all bit widths.

Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Tested-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
This commit is contained in:
Jason Ekstrand
2018-10-22 15:35:06 -05:00
committed by Jason Ekstrand
parent 80e8dfe9de
commit 2fe8708ffd

View File

@@ -24,8 +24,8 @@ def op_bit_sizes(op):
return sorted(list(sizes)) if sizes is not None else None
def get_const_field(type_):
if type_ == "bool32":
return "u32"
if type_base_type(type_) == 'bool':
return 'i' + str(type_size(type_))
elif type_ == "float16":
return "u16"
else:
@@ -240,8 +240,11 @@ unpack_half_1x16(uint16_t u)
typedef float float16_t;
typedef float float32_t;
typedef double float64_t;
typedef bool bool8_t;
typedef bool bool16_t;
typedef bool bool32_t;
% for type in ["float", "int", "uint"]:
typedef bool bool64_t;
% for type in ["float", "int", "uint", "bool"]:
% for width in type_sizes(type):
struct ${type}${width}_vec {
${type}${width}_t x;
@@ -252,13 +255,6 @@ struct ${type}${width}_vec {
% endfor
% endfor
struct bool32_vec {
bool x;
bool y;
bool z;
bool w;
};
<%def name="evaluate_op(op, bit_size)">
<%
output_type = type_add_size(op.output_type, bit_size)
@@ -278,9 +274,7 @@ struct bool32_vec {
const struct ${input_types[j]}_vec src${j} = {
% for k in range(op.input_sizes[j]):
% if input_types[j] == "bool32":
_src[${j}].u32[${k}] != 0,
% elif input_types[j] == "float16":
% if input_types[j] == "float16":
_mesa_half_to_float(_src[${j}].u16[${k}]),
% else:
_src[${j}].${get_const_field(input_types[j])}[${k}],
@@ -305,8 +299,6 @@ struct bool32_vec {
% elif "src" + str(j) not in op.const_expr:
## Avoid unused variable warnings
<% continue %>
% elif input_types[j] == "bool32":
const bool src${j} = _src[${j}].u32[_i] != 0;
% elif input_types[j] == "float16":
const float src${j} =
_mesa_half_to_float(_src[${j}].u16[_i]);
@@ -329,9 +321,9 @@ struct bool32_vec {
## Store the current component of the actual destination to the
## value of dst.
% if output_type == "bool32":
## Sanitize the C value to a proper NIR bool
_dst_val.u32[_i] = dst ? NIR_TRUE : NIR_FALSE;
% if output_type.startswith("bool"):
## Sanitize the C value to a proper NIR 0/-1 bool
_dst_val.${get_const_field(output_type)}[_i] = -(int)dst;
% elif output_type == "float16":
_dst_val.u16[_i] = _mesa_float_to_half(dst);
% else:
@@ -359,8 +351,8 @@ struct bool32_vec {
## the actual destination.
% for k in range(op.output_size):
% if output_type == "bool32":
## Sanitize the C value to a proper NIR bool
_dst_val.u32[${k}] = dst.${"xyzw"[k]} ? NIR_TRUE : NIR_FALSE;
## Sanitize the C value to a proper NIR 0/-1 bool
_dst_val.${get_const_field(output_type)}[${k}] = -(int)dst.${"xyzw"[k]};
% elif output_type == "float16":
_dst_val.u16[${k}] = _mesa_float_to_half(dst.${"xyzw"[k]});
% else: