summaryrefslogtreecommitdiffstats
path: root/libclc/generic/lib/shared
diff options
context:
space:
mode:
authorTom Stellard <thomas.stellard@amd.com>2013-06-26 18:22:05 +0000
committerTom Stellard <thomas.stellard@amd.com>2013-06-26 18:22:05 +0000
commit66ecbc7c18f4f923b41ead5f2177ff5f64b5df57 (patch)
treeb9bcfebf47c3f8dc65e600e72d0247ee606fe4b4 /libclc/generic/lib/shared
parentc0af47de001469015fba7208248f89235a69b3b8 (diff)
downloadbcm5719-llvm-66ecbc7c18f4f923b41ead5f2177ff5f64b5df57.tar.gz
bcm5719-llvm-66ecbc7c18f4f923b41ead5f2177ff5f64b5df57.zip
libclc: Initial vload implementation
Should work for all targets and data types. Completely unoptimized. Patch by: Aaron Watry llvm-svn: 185006
Diffstat (limited to 'libclc/generic/lib/shared')
-rw-r--r--libclc/generic/lib/shared/vload.cl47
1 files changed, 47 insertions, 0 deletions
diff --git a/libclc/generic/lib/shared/vload.cl b/libclc/generic/lib/shared/vload.cl
new file mode 100644
index 00000000000..24d82400f84
--- /dev/null
+++ b/libclc/generic/lib/shared/vload.cl
@@ -0,0 +1,47 @@
+#include <clc/clc.h>
+
+#define VLOAD_VECTORIZE(PRIM_TYPE, ADDR_SPACE) \
+ _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##2 vload2(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
+ return (PRIM_TYPE##2)(x[offset] , x[offset+1]); \
+ } \
+\
+ _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##3 vload3(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
+ return (PRIM_TYPE##3)(x[offset] , x[offset+1], x[offset+2]); \
+ } \
+\
+ _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##4 vload4(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
+ return (PRIM_TYPE##4)(x[offset], x[offset+1], x[offset+2], x[offset+3]); \
+ } \
+\
+ _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##8 vload8(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
+ return (PRIM_TYPE##8)(vload4(offset, x), vload4(offset+4, x)); \
+ } \
+\
+ _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##16 vload16(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
+ return (PRIM_TYPE##16)(vload8(offset, x), vload8(offset+8, x)); \
+ } \
+
+#define VLOAD_ADDR_SPACES(SCALAR_GENTYPE) \
+ VLOAD_VECTORIZE(SCALAR_GENTYPE, __private) \
+ VLOAD_VECTORIZE(SCALAR_GENTYPE, __local) \
+ VLOAD_VECTORIZE(SCALAR_GENTYPE, __constant) \
+ VLOAD_VECTORIZE(SCALAR_GENTYPE, __global) \
+
+#define VLOAD_TYPES() \
+ VLOAD_ADDR_SPACES(char) \
+ VLOAD_ADDR_SPACES(uchar) \
+ VLOAD_ADDR_SPACES(short) \
+ VLOAD_ADDR_SPACES(ushort) \
+ VLOAD_ADDR_SPACES(int) \
+ VLOAD_ADDR_SPACES(uint) \
+ VLOAD_ADDR_SPACES(long) \
+ VLOAD_ADDR_SPACES(ulong) \
+ VLOAD_ADDR_SPACES(float) \
+
+VLOAD_TYPES()
+
+#ifdef cl_khr_fp64
+#pragma OPENCL EXTENSION cl_khr_fp64 : enable
+ VLOAD_ADDR_SPACES(double)
+#endif
+
OpenPOWER on IntegriCloud