These get slightly wrong results for zero and the denorms and also don't handle the Inf/NaN stuff correctly, but are much more efficient than the full versions of these routines.
33 lines
754 B
Plaintext
33 lines
754 B
Plaintext
|
|
export uniform int width() { return programCount; }
|
|
|
|
export void f_v(uniform float RET[]) {
|
|
float sum = 0;
|
|
int errors = 0;
|
|
|
|
// We should match up except for the denorms (0->1023) and the inf/nan
|
|
// ranges.
|
|
for (uniform int i = 1024; i < 32768-1024; ++i) {
|
|
unsigned int16 h = i;
|
|
float f = half_to_float_fast(i);
|
|
h = float_to_half_fast(f);
|
|
|
|
if (i != h)
|
|
++errors;
|
|
}
|
|
|
|
for (uniform int i = 32768+1024; i < 65536-1024; ++i) {
|
|
unsigned int16 h = i;
|
|
float f = half_to_float_fast(i);
|
|
h = float_to_half_fast(f);
|
|
|
|
if (i != h)
|
|
++errors;
|
|
}
|
|
RET[programIndex] = errors;
|
|
}
|
|
|
|
export void result(uniform float RET[]) {
|
|
RET[programIndex] = 0;
|
|
}
|