Specifically, now we can work through phi nodes in the IR to detect cases
where an index value is actually the same across lanes or is linear across
the lanes. For example, this is a loop that used to require gathers but
is now turned into vector loads:
for (int i = programIndex; i < 16; i += programCount)
sum += a[i];
Fixes issue #107.
14 lines
334 B
Plaintext
14 lines
334 B
Plaintext
|
|
export uniform int width() { return programCount; }
|
|
|
|
export void f_f(uniform float RET[], uniform float aFOO[]) {
|
|
float sum = 0;
|
|
for (int i = programIndex; i < 16; i += programCount)
|
|
sum += aFOO[i];
|
|
RET[programIndex] = reduce_add(sum);
|
|
}
|
|
|
|
export void result(uniform float RET[]) {
|
|
RET[programIndex] = 136;
|
|
}
|