[PATCH 1/9] amdgpu/half_rsqrt: Switch implementation to native_rsqrt

Runtimes OpenCL
1

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

2

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

3

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

4

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

5

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

6

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

7

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

8

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

9

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

10

ping.

Jan

11

> Passes CTS on carrizo
> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
> ---
> amdgpu/lib/SOURCES | 1 +
> amdgpu/lib/math/half_recip.cl | 6 ++++++
> 2 files changed, 7 insertions(+)
> create mode 100644 amdgpu/lib/math/half_recip.cl
>
> diff --git a/amdgpu/lib/SOURCES b/amdgpu/lib/SOURCES
> index c6dc3bd..b11cbde 100644
> --- a/amdgpu/lib/SOURCES
> +++ b/amdgpu/lib/SOURCES
> @@ -7,6 +7,7 @@ math/half_exp2.cl
> math/half_log.cl
> math/half_log10.cl
> math/half_log2.cl
> +math/half_recip.cl
> math/half_rsqrt.cl
> math/half_sqrt.cl
> math/nextafter.cl
> diff --git a/amdgpu/lib/math/half_recip.cl b/amdgpu/lib/math/half_recip.cl
> new file mode 100644
> index 0000000..f1e0e4c
> --- /dev/null
> +++ b/amdgpu/lib/math/half_recip.cl
> @@ -0,0 +1,6 @@
> +#include <clc/clc.h>
> +
> +#define __CLC_FUNC recip
> +#define __FLOAT_ONLY
> +#define __CLC_BODY <half_native_unary.inc>
> +#include <clc/math/gentype.inc>

ping.

ping2

12

Passes CTS on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
---
amdgpu/lib/SOURCES | 1 +
amdgpu/lib/math/half_recip.cl | 6 ++++++
2 files changed, 7 insertions(+)
create mode 100644 amdgpu/lib/math/half_recip.cl

diff --git a/amdgpu/lib/SOURCES b/amdgpu/lib/SOURCES
index c6dc3bd..b11cbde 100644
--- a/amdgpu/lib/SOURCES
+++ b/amdgpu/lib/SOURCES
@@ -7,6 +7,7 @@ math/half_exp2.cl
math/half_log.cl
math/half_log10.cl
math/half_log2.cl
+math/half_recip.cl
math/half_rsqrt.cl
math/half_sqrt.cl
math/nextafter.cl
diff --git a/amdgpu/lib/math/half_recip.cl b/amdgpu/lib/math/half_recip.cl
new file mode 100644
index 0000000..f1e0e4c
--- /dev/null
+++ b/amdgpu/lib/math/half_recip.cl
@@ -0,0 +1,6 @@
+#include <clc/clc.h>
+
+#define __CLC_FUNC recip
+#define __FLOAT_ONLY
+#define __CLC_BODY <half_native_unary.inc>
+#include <clc/math/gentype.inc>

ping.

ping2

LGTM for the series.

-Tom