summaryrefslogtreecommitdiffstats
path: root/libclc/amdgpu/lib/math
diff options
context:
space:
mode:
authorJan Vesely <jan.vesely@rutgers.edu>2018-05-17 22:55:30 +0000
committerJan Vesely <jan.vesely@rutgers.edu>2018-05-17 22:55:30 +0000
commit70a270da5f4a27b670cba1cb8148fcce5c094f4f (patch)
treeba5043901fab059f1a5ccfb2578156c62ec4c027 /libclc/amdgpu/lib/math
parentc762666e8747841ab7dd785415e1354a1682e954 (diff)
downloadbcm5719-llvm-70a270da5f4a27b670cba1cb8148fcce5c094f4f.tar.gz
bcm5719-llvm-70a270da5f4a27b670cba1cb8148fcce5c094f4f.zip
Add initial support for half precision builtins
v2: fix fmax implementation use consistent checks for __CLC_FP_SIZE add missing TODOs fix whitespace in definitions.h v3: undef ZERO in modf.inc Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> reviewer: Jeroen Ketema <j.ketema@xs4all.nl> Reviewed-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 332677
Diffstat (limited to 'libclc/amdgpu/lib/math')
-rw-r--r--libclc/amdgpu/lib/math/nextafter.cl5
-rw-r--r--libclc/amdgpu/lib/math/sqrt.cl7
2 files changed, 12 insertions, 0 deletions
diff --git a/libclc/amdgpu/lib/math/nextafter.cl b/libclc/amdgpu/lib/math/nextafter.cl
index 5b4521d21c2..b290da0e417 100644
--- a/libclc/amdgpu/lib/math/nextafter.cl
+++ b/libclc/amdgpu/lib/math/nextafter.cl
@@ -8,3 +8,8 @@ _CLC_DEFINE_BINARY_BUILTIN(float, nextafter, __clc_nextafter, float, float)
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
_CLC_DEFINE_BINARY_BUILTIN(double, nextafter, __clc_nextafter, double, double)
#endif
+
+#ifdef cl_khr_fp16
+#pragma OPENCL EXTENSION cl_khr_fp16 : enable
+_CLC_DEFINE_BINARY_BUILTIN(half, nextafter, __clc_nextafter, half, half)
+#endif
diff --git a/libclc/amdgpu/lib/math/sqrt.cl b/libclc/amdgpu/lib/math/sqrt.cl
index 395a3f9fb21..55626003316 100644
--- a/libclc/amdgpu/lib/math/sqrt.cl
+++ b/libclc/amdgpu/lib/math/sqrt.cl
@@ -26,6 +26,13 @@
_CLC_DEFINE_UNARY_BUILTIN(float, sqrt, __clc_sqrt, float)
+#ifdef cl_khr_fp16
+
+#pragma OPENCL EXTENSION cl_khr_fp16 : enable
+_CLC_DEFINE_UNARY_BUILTIN(half, sqrt, __clc_sqrt, half)
+
+#endif
+
#ifdef cl_khr_fp64
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
OpenPOWER on IntegriCloud