[Libclc-dev] [PATCH 2/4] relational: Implement isgreaterequal

[Jeroen Ketema]

I’m wondering: Wouldn’t it be better to extend the builtins to handle vectors properly, or would that break other things?

Jeroen

On 11 Jun 2014, at 20:15, Aaron Watry <awatry at gmail.com> wrote:

> Signed-off-by: Aaron Watry <awatry at gmail.com>
> ---
> generic/include/clc/clc.h                       |  3 ++-
> generic/include/clc/relational/isgreaterequal.h | 18 +++++++++++++
> generic/lib/SOURCES                             |  1 +
> generic/lib/relational/isgreaterequal.cl        | 36 +++++++++++++++++++++++++
> 4 files changed, 57 insertions(+), 1 deletion(-)
> create mode 100644 generic/include/clc/relational/isgreaterequal.h
> create mode 100644 generic/lib/relational/isgreaterequal.cl
> 
> diff --git a/generic/include/clc/clc.h b/generic/include/clc/clc.h
> index 040ed2c..a220da5 100644
> --- a/generic/include/clc/clc.h
> +++ b/generic/include/clc/clc.h
> @@ -104,9 +104,10 @@
> /* 6.11.6 Relational Functions */
> #include <clc/relational/any.h>
> #include <clc/relational/bitselect.h>
> +#include <clc/relational/isgreater.h>
> +#include <clc/relational/isgreaterequal.h>
> #include <clc/relational/isnan.h>
> #include <clc/relational/select.h>
> -#include <clc/relational/isgreater.h>
> 
> /* 6.11.8 Synchronization Functions */
> #include <clc/synchronization/cl_mem_fence_flags.h>
> diff --git a/generic/include/clc/relational/isgreaterequal.h b/generic/include/clc/relational/isgreaterequal.h
> new file mode 100644
> index 0000000..5274714
> --- /dev/null
> +++ b/generic/include/clc/relational/isgreaterequal.h
> @@ -0,0 +1,18 @@
> +
> +#define _CLC_ISGREATEREQUAL_DECL(TYPE, RETTYPE) \
> +  _CLC_OVERLOAD _CLC_DECL RETTYPE isgreaterequal(TYPE x, TYPE y);
> +
> +#define _CLC_VECTOR_ISGREATEREQUAL_DECL(TYPE, RETTYPE) \
> +  _CLC_ISGREATEREQUAL_DECL(TYPE##2, RETTYPE##2)  \
> +  _CLC_ISGREATEREQUAL_DECL(TYPE##3, RETTYPE##3)  \
> +  _CLC_ISGREATEREQUAL_DECL(TYPE##4, RETTYPE##4)  \
> +  _CLC_ISGREATEREQUAL_DECL(TYPE##8, RETTYPE##8)  \
> +  _CLC_ISGREATEREQUAL_DECL(TYPE##16, RETTYPE##16)
> +
> +_CLC_ISGREATEREQUAL_DECL(float, int)
> +_CLC_VECTOR_ISGREATEREQUAL_DECL(float, int)
> +
> +#ifdef cl_khr_fp64
> +_CLC_ISGREATEREQUAL_DECL(double, int)
> +_CLC_VECTOR_ISGREATEREQUAL_DECL(double, long)
> +#endif
> \ No newline at end of file
> diff --git a/generic/lib/SOURCES b/generic/lib/SOURCES
> index 6479b53..9b8cf89 100644
> --- a/generic/lib/SOURCES
> +++ b/generic/lib/SOURCES
> @@ -36,6 +36,7 @@ math/nextafter.cl
> math/sincos.cl
> relational/any.cl
> relational/isgreater.cl
> +relational/isgreaterequal.cl
> relational/isnan.cl
> shared/clamp.cl
> shared/max.cl
> diff --git a/generic/lib/relational/isgreaterequal.cl b/generic/lib/relational/isgreaterequal.cl
> new file mode 100644
> index 0000000..da47aa3
> --- /dev/null
> +++ b/generic/lib/relational/isgreaterequal.cl
> @@ -0,0 +1,36 @@
> +#include <clc/clc.h>
> +
> +//Note: It would be nice to use __builtin_isgreaterequal, but that seems to only take scalar values as input, which will
> +//      produce incorrect output for vector input types.
> +//
> +//      For the the same reason (1 vs -1 output), we can't use the _CLC_DEFINE_BINARY_BUILTIN macro here as that expands
> +//      all vector operations to multiple scalar operations
> +
> +#define _CLC_DEFINE_ISGREATEREQUAL(RET_TYPE, FUNCTION, ARG1_TYPE, ARG2_TYPE) \
> +_CLC_DEF _CLC_OVERLOAD RET_TYPE FUNCTION(ARG1_TYPE x, ARG2_TYPE y) { \
> +  return (x >= y); \
> +} \
> +
> +_CLC_DEFINE_ISGREATEREQUAL(int, isgreaterequal, float, float)
> +_CLC_DEFINE_ISGREATEREQUAL(int2, isgreaterequal, float2, float2)
> +_CLC_DEFINE_ISGREATEREQUAL(int3, isgreaterequal, float3, float3)
> +_CLC_DEFINE_ISGREATEREQUAL(int4, isgreaterequal, float4, float4)
> +_CLC_DEFINE_ISGREATEREQUAL(int8, isgreaterequal, float8, float8)
> +_CLC_DEFINE_ISGREATEREQUAL(int16, isgreaterequal, float16, float16)
> +
> +#ifdef cl_khr_fp64
> +
> +#pragma OPENCL EXTENSION cl_khr_fp64 : enable
> +
> +// The scalar version of isgreaterequal(double) returns an int, but the vector versions
> +// return long.
> +_CLC_DEFINE_ISGREATEREQUAL(int, isgreaterequal, double, double)
> +_CLC_DEFINE_ISGREATEREQUAL(long2, isgreaterequal, double2, double2)
> +_CLC_DEFINE_ISGREATEREQUAL(long3, isgreaterequal, double3, double3)
> +_CLC_DEFINE_ISGREATEREQUAL(long4, isgreaterequal, double4, double4)
> +_CLC_DEFINE_ISGREATEREQUAL(long8, isgreaterequal, double8, double8)
> +_CLC_DEFINE_ISGREATEREQUAL(long16, isgreaterequal, double16, double16)
> +
> +#endif
> +
> +#undef _CLC_DEFINE_ISGREATEREQUAL
> \ No newline at end of file
> -- 
> 1.9.1
> 
> 
> _______________________________________________
> Libclc-dev mailing list
> Libclc-dev at pcc.me.uk
> http://www.pcc.me.uk/cgi-bin/mailman/listinfo/libclc-dev