libclc: Enable assembly versions of int2 load/store to global address space

The bug in R600 which prevented them from working has been mitigated.

Signed-off-by: Aaron Watry<awatry@gmail.com>

2 files changed, 20 insertions, 18 deletions

diff --git a/generic/lib/shared/vload.cl b/generic/lib/shared/vload.cl
index e47aa2e..dd28347 100644
--- a/generic/lib/shared/vload.cl
+++ b/generic/lib/shared/vload.cl
@@ -51,26 +51,24 @@ VLOAD_VECTORIZE(uint, __private)
 VLOAD_VECTORIZE(uint, __local)
 VLOAD_VECTORIZE(uint, __constant)
 
-_CLC_OVERLOAD _CLC_DEF int2 vload2(size_t offset, const global int *x) {
-  return (int2)(x[offset] , x[offset+1]);
-}
 _CLC_OVERLOAD _CLC_DEF int3 vload3(size_t offset, const global int *x) {
   return (int3)(vload2(offset, x), x[offset+2]);
 }
-_CLC_OVERLOAD _CLC_DEF uint2 vload2(size_t offset, const global uint *x) {
-  return (uint2)(x[offset] , x[offset+1]);
-}
 _CLC_OVERLOAD _CLC_DEF uint3 vload3(size_t offset, const global uint *x) {
   return (uint3)(vload2(offset, x), x[offset+2]);
 }
         
-/*Note: It is known that R600 doesn't support load <2 x ?> and <3 x ?>... so
- * they aren't actually overridden here
+/*Note: R600 doesn't support load <3 x ?>... so
+ * those functions aren't actually overridden here
  */
+_CLC_DECL int2 __clc_vload2_int__global(size_t offset, const __global int *);
 _CLC_DECL int4 __clc_vload4_int__global(size_t offset, const __global int *);
 _CLC_DECL int8 __clc_vload8_int__global(size_t offset, const __global int *);
 _CLC_DECL int16 __clc_vload16_int__global(size_t offset, const __global int *);
 
+_CLC_OVERLOAD _CLC_DEF int2 vload2(size_t offset, const global int *x) {
+  return __clc_vload2_int__global(offset, x);
+}
 _CLC_OVERLOAD _CLC_DEF int4 vload4(size_t offset, const global int *x) {
   return __clc_vload4_int__global(offset, x);
 }
@@ -81,10 +79,14 @@ _CLC_OVERLOAD _CLC_DEF int16 vload16(size_t offset, const global int *x) {
   return __clc_vload16_int__global(offset, x);
 }
 
+_CLC_DECL uint2 __clc_vload2_uint__global(size_t offset, const __global uint *);
 _CLC_DECL uint4 __clc_vload4_uint__global(size_t offset, const __global uint *);
 _CLC_DECL uint8 __clc_vload8_uint__global(size_t offset, const __global uint *);
 _CLC_DECL uint16 __clc_vload16_uint__global(size_t offset, const __global uint *);
 
+_CLC_OVERLOAD _CLC_DEF uint2 vload2(size_t offset, const global uint *x) {
+  return __clc_vload2_uint__global(offset, x);
+}
 _CLC_OVERLOAD _CLC_DEF uint4 vload4(size_t offset, const global uint *x) {
   return __clc_vload4_uint__global(offset, x);
 }
diff --git a/generic/lib/shared/vstore.cl b/generic/lib/shared/vstore.cl
index c6d9551..c8b8cd5 100644
--- a/generic/lib/shared/vstore.cl
+++ b/generic/lib/shared/vstore.cl
@@ -56,32 +56,28 @@ 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
+/*Note: R600 doesn't support store <3 x ?>... so
+ * those functions aren't actually overridden here... lowest-common-denominator
  */
+_CLC_DECL void __clc_vstore2_int__global(int2 vec, size_t offset, __global int *);
 _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 vstore2(int2 vec, size_t offset, global int *x) {
+    __clc_vstore2_int__global(vec, offset, x);
+}
 _CLC_OVERLOAD _CLC_DEF void vstore4(int4 vec, size_t offset, global int *x) {
     __clc_vstore4_int__global(vec, offset, x);
 }
@@ -92,10 +88,14 @@ _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_vstore2_uint__global(uint2 vec, size_t offset, __global uint *);
 _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 vstore2(uint2 vec, size_t offset, global uint *x) {
+    __clc_vstore2_uint__global(vec, offset, x);
+}
 _CLC_OVERLOAD _CLC_DEF void vstore4(uint4 vec, size_t offset, global uint *x) {
     __clc_vstore4_uint__global(vec, offset, x);
 }