Displaying 2 results from an estimated 2 matches for "__cpu_float2_acospi_float2".
2011 Oct 20
0
[LLVMdev] Re : ANN: libclc (OpenCL C library implementation)
..._PI;
end
----
Is compiled to these fragments, one for each vector type (float2, float3, etc) :
----
// In stdlib_def.h : what the OpenCL C kernel sees
float2 OVERLOAD acospi(float2 x);
// In stdlib_impl.h : what gets compiled to LLVM IR at Clover compile time, and then linked to each kernel
void __cpu_float2_acospi_float2(float *result, float *x);
float2 OVERLOAD acospi(float2 x)
{
float2 result;
__cpu_float2_acospi_float2((float *)&result, (float *)&x);
return result;
}
// __cpu_float2_acospi_float2 is a function implemented in the Clover .so library, using llvm::JIT::registerLasyFunctionCrea...
2011 Oct 20
5
[LLVMdev] ANN: libclc (OpenCL C library implementation)
Hi Carlos,
On 10/20/11 9:54 AM, Carlos Sánchez de La Lama wrote:
>> The project started as a use-case for our "Whole-Function Vectorization"
>> library, which allows to transform a function to compute the same as W
>> executions of the original code by using SIMD instructions (W = 4 for
>> SSE/AltiVec, 8 for AVX).
>
> Quite interesting. We were planning to