gallivm: Increase lp_build_rsqrt() precision.
Add an iteration step, which makes rqsqrt precision go from 12bits to 24, and fixes RSQ/NRM test case of PSPrecision/VSPrevision DCTs. There are no uses of this function outside shader translation.
This commit is contained in:
@@ -1645,7 +1645,7 @@ lp_build_rsqrt(struct lp_build_context *bld,
|
||||
assert(type.floating);
|
||||
|
||||
if (util_cpu_caps.has_sse && type.width == 32 && type.length == 4) {
|
||||
const unsigned num_iterations = 0;
|
||||
const unsigned num_iterations = 1;
|
||||
LLVMValueRef res;
|
||||
unsigned i;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user