[Beignet] [PATCH] revise built-in function "shuffle"

[Zhigang Gong]

On Wed, Jul 24, 2013 at 02:58:28PM +0800, Homer Hsing wrote:
> Signed-off-by: Homer Hsing <homer.xing at intel.com>
> ---
>  backend/src/ocl_stdlib.tmpl.h | 68 +++++++++++++++++++++----------------------
>  1 file changed, 34 insertions(+), 34 deletions(-)
> 
> diff --git a/backend/src/ocl_stdlib.tmpl.h b/backend/src/ocl_stdlib.tmpl.h
> index 387e6fb..92a822a 100644
> --- a/backend/src/ocl_stdlib.tmpl.h
> +++ b/backend/src/ocl_stdlib.tmpl.h
> @@ -1106,68 +1106,69 @@ DECL_UNTYPED_RW_ALL(float)
>  #define maxmag __gen_ocl_internal_maxmag
>  #define minmag __gen_ocl_internal_minmag
>  
> +/////////////////////////////////////////////////////////////////////////////
>  // Miscellaneous Vector Functions (see 6.11.12 of OCL 1.1 spec)
>  /////////////////////////////////////////////////////////////////////////////
>  #define DEC2(TYPE, XTYPE) \
>    INLINE_OVERLOADABLE TYPE##2 shuffle(XTYPE x, uint2 mask) { \
>      TYPE##2 y; \
> -    y.s0 = ((TYPE *) &x)[mask.s0 & 1]; \
> -    y.s1 = ((TYPE *) &x)[mask.s1 & 1]; \
> +    y.s0 = ((TYPE *) &x)[mask.s0 & (vec_step(x) - 1)]; \
> +    y.s1 = ((TYPE *) &x)[mask.s1 & (vec_step(x) - 1)]; \
>      return y; \
>    }
>  
>  #define DEC3(TYPE, XTYPE) \
>    INLINE_OVERLOADABLE TYPE##3 shuffle(XTYPE x, uint3 mask) { \
>      TYPE##3 y; \
> -    y.s0 = ((TYPE *) &x)[mask.s0 & 3]; \
> -    y.s1 = ((TYPE *) &x)[mask.s1 & 3]; \
> -    y.s2 = ((TYPE *) &x)[mask.s2 & 3]; \
> +    y.s0 = ((TYPE *) &x)[mask.s0 & (vec_step(x) - 1)]; \
> +    y.s1 = ((TYPE *) &x)[mask.s1 & (vec_step(x) - 1)]; \
> +    y.s2 = ((TYPE *) &x)[mask.s2 & (vec_step(x) - 1)]; \
>      return y; \
>    }
In misc vector function section,  gentypen (or gentypem) to indicate the built-in 
data types {char|uchar|...}{2|4|8|16} And there is no 3-components vector type defined
here.
>  
>  #define DEC4(TYPE, XTYPE) \
>    INLINE_OVERLOADABLE TYPE##4 shuffle(XTYPE x, uint4 mask) { \
>      TYPE##4 y; \
> -    y.s0 = ((TYPE *) &x)[mask.s0 & 3]; \
> -    y.s1 = ((TYPE *) &x)[mask.s1 & 3]; \
> -    y.s2 = ((TYPE *) &x)[mask.s2 & 3]; \
> -    y.s3 = ((TYPE *) &x)[mask.s3 & 3]; \
> +    y.s0 = ((TYPE *) &x)[mask.s0 & (vec_step(x) - 1)]; \
> +    y.s1 = ((TYPE *) &x)[mask.s1 & (vec_step(x) - 1)]; \
> +    y.s2 = ((TYPE *) &x)[mask.s2 & (vec_step(x) - 1)]; \
> +    y.s3 = ((TYPE *) &x)[mask.s3 & (vec_step(x) - 1)]; \
>      return y; \
>    }
>  
>  #define DEC8(TYPE, XTYPE) \
>    INLINE_OVERLOADABLE TYPE##8 shuffle(XTYPE x, uint8 mask) { \
>      TYPE##8 y; \
> -    y.s0 = ((TYPE *) &x)[mask.s0 & 7]; \
> -    y.s1 = ((TYPE *) &x)[mask.s1 & 7]; \
> -    y.s2 = ((TYPE *) &x)[mask.s2 & 7]; \
> -    y.s3 = ((TYPE *) &x)[mask.s3 & 7]; \
> -    y.s4 = ((TYPE *) &x)[mask.s4 & 7]; \
> -    y.s5 = ((TYPE *) &x)[mask.s5 & 7]; \
> -    y.s6 = ((TYPE *) &x)[mask.s6 & 7]; \
> -    y.s7 = ((TYPE *) &x)[mask.s7 & 7]; \
> +    y.s0 = ((TYPE *) &x)[mask.s0 & (vec_step(x) - 1)]; \
> +    y.s1 = ((TYPE *) &x)[mask.s1 & (vec_step(x) - 1)]; \
> +    y.s2 = ((TYPE *) &x)[mask.s2 & (vec_step(x) - 1)]; \
> +    y.s3 = ((TYPE *) &x)[mask.s3 & (vec_step(x) - 1)]; \
> +    y.s4 = ((TYPE *) &x)[mask.s4 & (vec_step(x) - 1)]; \
> +    y.s5 = ((TYPE *) &x)[mask.s5 & (vec_step(x) - 1)]; \
> +    y.s6 = ((TYPE *) &x)[mask.s6 & (vec_step(x) - 1)]; \
> +    y.s7 = ((TYPE *) &x)[mask.s7 & (vec_step(x) - 1)]; \
>      return y; \
>    }
>  
>  #define DEC16(TYPE, XTYPE) \
>    INLINE_OVERLOADABLE TYPE##16 shuffle(XTYPE x, uint16 mask) { \
>      TYPE##16 y; \
> -    y.s0 = ((TYPE *) &x)[mask.s0 & 15]; \
> -    y.s1 = ((TYPE *) &x)[mask.s1 & 15]; \
> -    y.s2 = ((TYPE *) &x)[mask.s2 & 15]; \
> -    y.s3 = ((TYPE *) &x)[mask.s3 & 15]; \
> -    y.s4 = ((TYPE *) &x)[mask.s4 & 15]; \
> -    y.s5 = ((TYPE *) &x)[mask.s5 & 15]; \
> -    y.s6 = ((TYPE *) &x)[mask.s6 & 15]; \
> -    y.s7 = ((TYPE *) &x)[mask.s7 & 15]; \
> -    y.s8 = ((TYPE *) &x)[mask.s8 & 15]; \
> -    y.s9 = ((TYPE *) &x)[mask.s9 & 15]; \
> -    y.sa = ((TYPE *) &x)[mask.sa & 15]; \
> -    y.sb = ((TYPE *) &x)[mask.sb & 15]; \
> -    y.sc = ((TYPE *) &x)[mask.sc & 15]; \
> -    y.sd = ((TYPE *) &x)[mask.sd & 15]; \
> -    y.se = ((TYPE *) &x)[mask.se & 15]; \
> -    y.sf = ((TYPE *) &x)[mask.sf & 15]; \
> +    y.s0 = ((TYPE *) &x)[mask.s0 & (vec_step(x) - 1)]; \
> +    y.s1 = ((TYPE *) &x)[mask.s1 & (vec_step(x) - 1)]; \
> +    y.s2 = ((TYPE *) &x)[mask.s2 & (vec_step(x) - 1)]; \
> +    y.s3 = ((TYPE *) &x)[mask.s3 & (vec_step(x) - 1)]; \
> +    y.s4 = ((TYPE *) &x)[mask.s4 & (vec_step(x) - 1)]; \
> +    y.s5 = ((TYPE *) &x)[mask.s5 & (vec_step(x) - 1)]; \
> +    y.s6 = ((TYPE *) &x)[mask.s6 & (vec_step(x) - 1)]; \
> +    y.s7 = ((TYPE *) &x)[mask.s7 & (vec_step(x) - 1)]; \
> +    y.s8 = ((TYPE *) &x)[mask.s8 & (vec_step(x) - 1)]; \
> +    y.s9 = ((TYPE *) &x)[mask.s9 & (vec_step(x) - 1)]; \
> +    y.sa = ((TYPE *) &x)[mask.sa & (vec_step(x) - 1)]; \
> +    y.sb = ((TYPE *) &x)[mask.sb & (vec_step(x) - 1)]; \
> +    y.sc = ((TYPE *) &x)[mask.sc & (vec_step(x) - 1)]; \
> +    y.sd = ((TYPE *) &x)[mask.sd & (vec_step(x) - 1)]; \
> +    y.se = ((TYPE *) &x)[mask.se & (vec_step(x) - 1)]; \
> +    y.sf = ((TYPE *) &x)[mask.sf & (vec_step(x) - 1)]; \
>      return y; \
>    }
>  
> @@ -1190,7 +1191,6 @@ DEF(float)
>  #undef DEC4
>  #undef DEC8
>  #undef DEC16
> -/////////////////////////////////////////////////////////////////////////////
>  
>  /////////////////////////////////////////////////////////////////////////////
>  // Synchronization functions
> -- 
> 1.8.1.2
> 
> _______________________________________________
> Beignet mailing list
> Beignet at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/beignet