[Libclc-dev] [PATCH 1/1] math: Fix log2 vectorization on non-fp64 hw
Jan Vesely via Libclc-dev
libclc-dev at lists.llvm.org
Mon Feb 8 11:39:49 PST 2016
Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
---
generic/lib/math/log2.cl | 2 ++
1 file changed, 2 insertions(+)
diff --git a/generic/lib/math/log2.cl b/generic/lib/math/log2.cl
index df6eeb2..8776a80 100644
--- a/generic/lib/math/log2.cl
+++ b/generic/lib/math/log2.cl
@@ -34,4 +34,6 @@
_CLC_UNARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, float, log2, float);
+#ifdef cl_khr_fp64
_CLC_UNARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, double, log2, double);
+#endif // cl_khr_fp64
--
2.5.0
More information about the Libclc-dev
mailing list