[Libclc-dev] [PATCH 16/14] native_powr: Switch implementation to native_exp2 and native_log2

[Jan Vesely via Libclc-dev]

Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
---
 generic/include/clc/math/native_powr.h | 8 +++++++-
 generic/lib/SOURCES                    | 1 +
 generic/lib/math/native_powr.cl        | 5 +++++
 generic/lib/math/native_powr.inc       | 5 +++++
 4 files changed, 18 insertions(+), 1 deletion(-)
 create mode 100644 generic/lib/math/native_powr.cl
 create mode 100644 generic/lib/math/native_powr.inc

diff --git a/generic/include/clc/math/native_powr.h b/generic/include/clc/math/native_powr.h
index e8a37d9..c31161a 100644
--- a/generic/include/clc/math/native_powr.h
+++ b/generic/include/clc/math/native_powr.h
@@ -1 +1,7 @@
-#define native_powr pow
+#define __CLC_BODY <clc/math/binary_decl_tt.inc>
+#define __CLC_FUNCTION native_powr
+
+#include <clc/math/gentype.inc>
+
+#undef __CLC_BODY
+#undef __CLC_FUNCTION
diff --git a/generic/lib/SOURCES b/generic/lib/SOURCES
index 355741c..ad5a743 100644
--- a/generic/lib/SOURCES
+++ b/generic/lib/SOURCES
@@ -127,6 +127,7 @@ math/native_exp2.cl
 math/native_log.cl
 math/native_log10.cl
 math/native_log2.cl
+math/native_powr.cl
 math/native_recip.cl
 math/native_rsqrt.cl
 math/native_sin.cl
diff --git a/generic/lib/math/native_powr.cl b/generic/lib/math/native_powr.cl
new file mode 100644
index 0000000..452bc6f
--- /dev/null
+++ b/generic/lib/math/native_powr.cl
@@ -0,0 +1,5 @@
+#include <clc/clc.h>
+
+#define __CLC_BODY <native_powr.inc>
+#define __FLOAT_ONLY
+#include <clc/math/gentype.inc>
diff --git a/generic/lib/math/native_powr.inc b/generic/lib/math/native_powr.inc
new file mode 100644
index 0000000..1e0d948
--- /dev/null
+++ b/generic/lib/math/native_powr.inc
@@ -0,0 +1,5 @@
+_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE native_powr(__CLC_GENTYPE x, __CLC_GENTYPE y) {
+  __builtin_assume(all(isgreaterequal(x, (__CLC_GENTYPE)0.0f)));
+  __CLC_INTN cond = isequal(x, (__CLC_GENTYPE)0.0f);
+  return select( native_exp2(y * native_log2(x)), (__CLC_GENTYPE)0.0f, cond);
+}
-- 
2.13.6