libclc: Initial vload implementation

Should work for all targets and data types.  Completely unoptimized.

Patch by: Aaron Watry

git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@185006 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 86 insertions, 0 deletions

diff --git a/generic/include/clc/clc.h b/generic/include/clc/clc.h
index d2858a8..7937003 100644
--- a/generic/include/clc/clc.h
+++ b/generic/include/clc/clc.h
@@ -71,6 +71,7 @@
 #include <clc/shared/clamp.h>
 #include <clc/shared/max.h>
 #include <clc/shared/min.h>
+#include <clc/shared/vload.h>
 
 /* 6.11.5 Geometric Functions */
 #include <clc/geometric/cross.h>
diff --git a/generic/include/clc/shared/vload.h b/generic/include/clc/shared/vload.h
new file mode 100644
index 0000000..93d0750
--- /dev/null
+++ b/generic/include/clc/shared/vload.h
@@ -0,0 +1,37 @@
+#define _CLC_VLOAD_DECL(PRIM_TYPE, VEC_TYPE, WIDTH, ADDR_SPACE) \
+  _CLC_OVERLOAD _CLC_DECL VEC_TYPE vload##WIDTH(size_t offset, const ADDR_SPACE PRIM_TYPE *x);
+
+#define _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, ADDR_SPACE) \
+  _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##2, 2, ADDR_SPACE) \
+  _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##3, 3, ADDR_SPACE) \
+  _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##4, 4, ADDR_SPACE) \
+  _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##8, 8, ADDR_SPACE) \
+  _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##16, 16, ADDR_SPACE)
+
+#define _CLC_VECTOR_VLOAD_PRIM1(PRIM_TYPE) \
+  _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, __private) \
+  _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, __local) \
+  _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, __constant) \
+  _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, __global) \
+
+#define _CLC_VECTOR_VLOAD_PRIM() \
+    _CLC_VECTOR_VLOAD_PRIM1(char) \
+    _CLC_VECTOR_VLOAD_PRIM1(uchar) \
+    _CLC_VECTOR_VLOAD_PRIM1(short) \
+    _CLC_VECTOR_VLOAD_PRIM1(ushort) \
+    _CLC_VECTOR_VLOAD_PRIM1(int) \
+    _CLC_VECTOR_VLOAD_PRIM1(uint) \
+    _CLC_VECTOR_VLOAD_PRIM1(long) \
+    _CLC_VECTOR_VLOAD_PRIM1(ulong) \
+    _CLC_VECTOR_VLOAD_PRIM1(float) \
+        
+#ifdef cl_khr_fp64
+#define _CLC_VECTOR_VLOAD() \
+  _CLC_VECTOR_VLOAD_PRIM1(double) \
+  _CLC_VECTOR_VLOAD_PRIM()
+#else
+#define _CLC_VECTOR_VLOAD() \
+  _CLC_VECTOR_VLOAD_PRIM()
+#endif
+
+_CLC_VECTOR_VLOAD()
diff --git a/generic/lib/SOURCES b/generic/lib/SOURCES
index 59eb9bb..5d9e3fa 100644
--- a/generic/lib/SOURCES
+++ b/generic/lib/SOURCES
@@ -23,5 +23,6 @@ relational/any.cl
 shared/clamp.cl
 shared/max.cl
 shared/min.cl
+shared/vload.cl
 workitem/get_global_id.cl
 workitem/get_global_size.cl
diff --git a/generic/lib/shared/vload.cl b/generic/lib/shared/vload.cl
new file mode 100644
index 0000000..24d8240
--- /dev/null
+++ b/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
+