Normal mul/add could not met the precision requirement of this case. Previously it passed because we will do mad optimization in backend. Use mad directly, so the test case does not depend on backend optimization.
Signed-off-by: Ruiling Song <[email protected]> --- kernels/compiler_menger_sponge_no_shadow.cl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernels/compiler_menger_sponge_no_shadow.cl b/kernels/compiler_menger_sponge_no_shadow.cl index 4de6c10..27b059a 100644 --- a/kernels/compiler_menger_sponge_no_shadow.cl +++ b/kernels/compiler_menger_sponge_no_shadow.cl @@ -15,7 +15,7 @@ typedef float4 vec4; // fmod is not like glsl mod! inline __attribute__((always_inline, overloadable)) -float glsl_mod(float x,float y) { return x-y*floor(x/y); } +float glsl_mod(float x,float y) { return mad( -y, floor(x/y), x); } inline __attribute__((always_inline, overloadable)) float2 glsl_mod(float2 a,float2 b) { return (float2)(glsl_mod(a.x,b.x), glsl_mod(a.y,b.y)); } inline __attribute__((always_inline, overloadable)) -- 1.7.9.5 _______________________________________________ Beignet mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/beignet
