This commit replaces the loop for calculating log base 2 for
non-x86-platforms in radeon.h with a clz (count leading zeroes)-based
version to simplify the code and, well, eliminate the loop.
Note: Thereâ??s no check for val=0 case, since x86-bsr is undefined for
that case too, that should be okay.
---
src/radeon.h | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/src/radeon.h b/src/radeon.h
index cbc7866..b1a1ce0 100644
--- a/src/radeon.h
+++ b/src/radeon.h
@@ -933,17 +933,16 @@ enum {
static __inline__ int
RADEONLog2(int val)
{
- int bits;
#if (defined __i386__ || defined __x86_64__) && (defined __GNUC__)
+ int bits;
+
__asm volatile("bsrl %1, %0"
: "=r" (bits)
: "c" (val)
);
return bits;
#else
- for (bits = 0; val != 0; val >>= 1, ++bits)
- ;
- return bits - 1;
+ return (31 - __builtin_clz(val));
#endif
}
--
1.7.9.5
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0001-Replace-loop-with-clz-to-calculate-log-base-2-on-non.patch
Type: text/x-patch
Size: 1229 bytes
Desc: not available
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20161128/9a1d9988/attachment.bin>
