summaryrefslogtreecommitdiff
path: root/generic/lib/shared/vstore.cl
diff options
context:
space:
mode:
Diffstat (limited to 'generic/lib/shared/vstore.cl')
-rw-r--r--generic/lib/shared/vstore.cl63
1 files changed, 57 insertions, 6 deletions
diff --git a/generic/lib/shared/vstore.cl b/generic/lib/shared/vstore.cl
index e88ccc5..5b84f47 100644
--- a/generic/lib/shared/vstore.cl
+++ b/generic/lib/shared/vstore.cl
@@ -15,10 +15,8 @@
} \
\
_CLC_OVERLOAD _CLC_DEF void vstore4(PRIM_TYPE##4 vec, size_t offset, ADDR_SPACE PRIM_TYPE *mem) { \
- mem[offset] = vec.s0; \
- mem[offset+1] = vec.s1; \
- mem[offset+2] = vec.s2; \
- mem[offset+3] = vec.s3; \
+ vstore2(vec.lo, offset, mem); \
+ vstore2(vec.hi, offset+2, mem); \
} \
\
_CLC_OVERLOAD _CLC_DEF void vstore8(PRIM_TYPE##8 vec, size_t offset, ADDR_SPACE PRIM_TYPE *mem) { \
@@ -36,13 +34,12 @@
VSTORE_VECTORIZE(SCALAR_GENTYPE, __local) \
VSTORE_VECTORIZE(SCALAR_GENTYPE, __global) \
+//int/uint are special... see below
#define VSTORE_TYPES() \
VSTORE_ADDR_SPACES(char) \
VSTORE_ADDR_SPACES(uchar) \
VSTORE_ADDR_SPACES(short) \
VSTORE_ADDR_SPACES(ushort) \
- VSTORE_ADDR_SPACES(int) \
- VSTORE_ADDR_SPACES(uint) \
VSTORE_ADDR_SPACES(long) \
VSTORE_ADDR_SPACES(ulong) \
VSTORE_ADDR_SPACES(float) \
@@ -54,3 +51,57 @@ VSTORE_TYPES()
VSTORE_ADDR_SPACES(double)
#endif
+VSTORE_VECTORIZE(int, __private)
+VSTORE_VECTORIZE(int, __local)
+VSTORE_VECTORIZE(uint, __private)
+VSTORE_VECTORIZE(uint, __local)
+
+_CLC_OVERLOAD _CLC_DEF void vstore2(int2 vec, size_t offset, global int *mem) {
+ mem[offset] = vec.s0;
+ mem[offset+1] = vec.s1;
+}
+_CLC_OVERLOAD _CLC_DEF void vstore3(int3 vec, size_t offset, global int *mem) {
+ mem[offset] = vec.s0;
+ mem[offset+1] = vec.s1;
+ mem[offset+2] = vec.s2;
+}
+_CLC_OVERLOAD _CLC_DEF void vstore2(uint2 vec, size_t offset, global uint *mem) {
+ mem[offset] = vec.s0;
+ mem[offset+1] = vec.s1;
+}
+_CLC_OVERLOAD _CLC_DEF void vstore3(uint3 vec, size_t offset, global uint *mem) {
+ mem[offset] = vec.s0;
+ mem[offset+1] = vec.s1;
+ mem[offset+2] = vec.s2;
+}
+
+/*Note: R600 probably doesn't support store <2 x ?> and <3 x ?>... so
+ * they aren't actually overridden here... lowest-common-denominator
+ */
+_CLC_DECL void __clc_vstore4_int__global(int4 vec, size_t offset, __global int *);
+_CLC_DECL void __clc_vstore8_int__global(int8 vec, size_t offset, __global int *);
+_CLC_DECL void __clc_vstore16_int__global(int16 vec, size_t offset, __global int *);
+
+_CLC_OVERLOAD _CLC_DEF void vstore4(int4 vec, size_t offset, global int *x) {
+ __clc_vstore4_int__global(vec, offset, x);
+}
+_CLC_OVERLOAD _CLC_DEF void vstore8(int8 vec, size_t offset, global int *x) {
+ __clc_vstore8_int__global(vec, offset, x);
+}
+_CLC_OVERLOAD _CLC_DEF void vstore16(int16 vec, size_t offset, global int *x) {
+ __clc_vstore16_int__global(vec, offset, x);
+}
+
+_CLC_DECL void __clc_vstore4_uint__global(uint4 vec, size_t offset, __global uint *);
+_CLC_DECL void __clc_vstore8_uint__global(uint8 vec, size_t offset, __global uint *);
+_CLC_DECL void __clc_vstore16_uint__global(uint16 vec, size_t offset, __global uint *);
+
+_CLC_OVERLOAD _CLC_DEF void vstore4(uint4 vec, size_t offset, global uint *x) {
+ __clc_vstore4_uint__global(vec, offset, x);
+}
+_CLC_OVERLOAD _CLC_DEF void vstore8(uint8 vec, size_t offset, global uint *x) {
+ __clc_vstore8_uint__global(vec, offset, x);
+}
+_CLC_OVERLOAD _CLC_DEF void vstore16(uint16 vec, size_t offset, global uint *x) {
+ __clc_vstore16_uint__global(vec, offset, x);
+}