[Libclc-dev] [PATCH 4/6] select: add vector implementation

[Jan Vesely via Libclc-dev]

Passes CTS on Carrizo

Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
---
 generic/include/clc/relational/select.h   | 12 +++++++-
 generic/include/clc/relational/select.inc | 25 ++++++++++++++++
 generic/lib/SOURCES                       |  1 +
 generic/lib/relational/select.cl          |  7 +++++
 generic/lib/relational/select.inc         | 47 +++++++++++++++++++++++++++++++
 5 files changed, 91 insertions(+), 1 deletion(-)
 create mode 100644 generic/include/clc/relational/select.inc
 create mode 100644 generic/lib/relational/select.cl
 create mode 100644 generic/lib/relational/select.inc

diff --git a/generic/include/clc/relational/select.h b/generic/include/clc/relational/select.h
index 33a6909..d20deae 100644
--- a/generic/include/clc/relational/select.h
+++ b/generic/include/clc/relational/select.h
@@ -1 +1,11 @@
-#define select(a, b, c) ((c) ? (b) : (a))
+/* Duplciate these so we don't have to distribute utils.h */
+#define __CLC_CONCAT(x, y) x ## y
+#define __CLC_XCONCAT(x, y) __CLC_CONCAT(x, y)
+
+#define __CLC_BODY <clc/relational/select.inc>
+#include <clc/math/gentype.inc>
+#define __CLC_BODY <clc/relational/select.inc>
+#include <clc/integer/gentype.inc>
+
+#undef __CLC_CONCAT
+#undef __CLC_XCONCAT
diff --git a/generic/include/clc/relational/select.inc b/generic/include/clc/relational/select.inc
new file mode 100644
index 0000000..2911009
--- /dev/null
+++ b/generic/include/clc/relational/select.inc
@@ -0,0 +1,25 @@
+#ifdef __CLC_SCALAR
+#define __CLC_VECSIZE
+#endif
+
+#if __CLC_FPSIZE == 64
+#define __CLC_S_GENTYPE __CLC_XCONCAT(long, __CLC_VECSIZE) 
+#define __CLC_U_GENTYPE __CLC_XCONCAT(ulong, __CLC_VECSIZE) 
+#elif __CLC_FPSIZE == 32
+#define __CLC_S_GENTYPE __CLC_XCONCAT(int, __CLC_VECSIZE) 
+#define __CLC_U_GENTYPE __CLC_XCONCAT(uint, __CLC_VECSIZE) 
+#elif __CLC_FPSIZE == 16
+#define __CLC_S_GENTYPE __CLC_XCONCAT(char, __CLC_VECSIZE) 
+#define __CLC_U_GENTYPE __CLC_XCONCAT(uchar, __CLC_VECSIZE) 
+#endif
+
+_CLC_OVERLOAD _CLC_DECL __CLC_GENTYPE select(__CLC_GENTYPE x, __CLC_GENTYPE y, __CLC_S_GENTYPE z);
+_CLC_OVERLOAD _CLC_DECL __CLC_GENTYPE select(__CLC_GENTYPE x, __CLC_GENTYPE y, __CLC_U_GENTYPE z);
+
+#ifdef __CLC_FPSIZE
+#undef __CLC_S_GENTYPE
+#undef __CLC_U_GENTYPE
+#endif
+#ifdef __CLC_SCALAR
+#undef __CLC_VECSIZE
+#endif
diff --git a/generic/lib/SOURCES b/generic/lib/SOURCES
index 13fe4fa..f9104a3 100644
--- a/generic/lib/SOURCES
+++ b/generic/lib/SOURCES
@@ -189,6 +189,7 @@ relational/isnormal.cl
 relational/isnotequal.cl
 relational/isordered.cl
 relational/isunordered.cl
+relational/select.cl
 relational/signbit.cl
 shared/clamp.cl
 shared/max.cl
diff --git a/generic/lib/relational/select.cl b/generic/lib/relational/select.cl
new file mode 100644
index 0000000..dc2e273
--- /dev/null
+++ b/generic/lib/relational/select.cl
@@ -0,0 +1,7 @@
+#include <clc/clc.h>
+#include <utils.h>
+
+#define __CLC_BODY <select.inc>
+#include <clc/math/gentype.inc>
+#define __CLC_BODY <select.inc>
+#include <clc/integer/gentype.inc>
diff --git a/generic/lib/relational/select.inc b/generic/lib/relational/select.inc
new file mode 100644
index 0000000..b990d26
--- /dev/null
+++ b/generic/lib/relational/select.inc
@@ -0,0 +1,47 @@
+#ifdef __CLC_SCALAR
+#define __CLC_VECSIZE
+#endif
+
+#if __CLC_FPSIZE == 64
+#define __CLC_S_GENTYPE __CLC_XCONCAT(long, __CLC_VECSIZE) 
+#define __CLC_U_GENTYPE __CLC_XCONCAT(ulong, __CLC_VECSIZE) 
+#elif __CLC_FPSIZE == 32
+#define __CLC_S_GENTYPE __CLC_XCONCAT(int, __CLC_VECSIZE) 
+#define __CLC_U_GENTYPE __CLC_XCONCAT(uint, __CLC_VECSIZE) 
+#elif __CLC_FPSIZE == 16
+#define __CLC_S_GENTYPE __CLC_XCONCAT(char, __CLC_VECSIZE) 
+#define __CLC_U_GENTYPE __CLC_XCONCAT(uchar, __CLC_VECSIZE) 
+#endif
+#ifdef __CLC_FPSIZE
+#define __CLC_GENSIZE   __CLC_FPSIZE
+#endif
+
+#define __CLC_AS_S_GENTYPE __CLC_XCONCAT(as_, __CLC_S_GENTYPE)
+#define __CLC_AS_GENTYPE __CLC_XCONCAT(as_, __CLC_GENTYPE)
+
+_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE select(__CLC_GENTYPE x, __CLC_GENTYPE y, __CLC_S_GENTYPE z)
+{
+#ifdef __CLC_SCALAR
+	return z ? y : x;
+#else
+	__CLC_S_GENTYPE bitmask = z >> (__CLC_GENSIZE - 1);
+	return __CLC_AS_GENTYPE(bitselect(__CLC_AS_S_GENTYPE(x), __CLC_AS_S_GENTYPE(y), bitmask));
+#endif
+}
+
+_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE select(__CLC_GENTYPE x, __CLC_GENTYPE y, __CLC_U_GENTYPE z)
+{
+	return select(x, y, __CLC_AS_S_GENTYPE(z));
+}
+
+#undef __CLC_AS_S_GENTYPE
+#undef __CLC_AS_GENTYPE
+
+#ifdef __CLC_FPSIZE
+#undef __CLC_S_GENTYPE
+#undef __CLC_U_GENTYPE
+#undef __CLC_GENSIZE
+#endif
+#ifdef __CLC_SCALAR
+#undef __CLC_VECSIZE
+#endif
-- 
2.14.3