Displaying 4 results from an estimated 4 matches for "kernel_funct".
2011 Nov 14
2
[LLVMdev] PTX backend fatal error
Hi everybody,
I am testing the PTX backend using the OpenCL NVIDIA SDK benchmarks.
Compiling the Histogram64.cl program I get a several backend errors.
I isolated one of them in the following kernel program:
__kernel void kernel_function(__global int *input) {
__local char localArray[16];
for(unsigned int index = 0; index < 16; ++index)
localArray[index] = 0;
input[0] = localArray[get_local_id(0)];
}
fatal error: error in backend: Cannot select:
0x5810cc0: i32,ch = load 0x57fa148,
0x5810ac0, 0x5...
2011 Nov 14
0
[LLVMdev] PTX backend fatal error
...berto.magni86 at gmail.com>wrote:
> Hi everybody,
>
> I am testing the PTX backend using the OpenCL NVIDIA SDK benchmarks.
> Compiling the Histogram64.cl program I get a several backend errors.
>
> I isolated one of them in the following kernel program:
>
> __kernel void kernel_function(__global int *input) {
> __local char localArray[16];
> for(unsigned int index = 0; index < 16; ++index)
> localArray[index] = 0;
> input[0] = localArray[get_local_id(0)];
> }
>
> fatal error: error in backend: Cannot select:
> 0x5810cc0: i32,ch = lo...
2011 Nov 14
1
[LLVMdev] PTX backend fatal error
...magni86 at gmail.com<mailto:alberto.magni86 at gmail.com>> wrote:
Hi everybody,
I am testing the PTX backend using the OpenCL NVIDIA SDK benchmarks.
Compiling the Histogram64.cl program I get a several backend errors.
I isolated one of them in the following kernel program:
__kernel void kernel_function(__global int *input) {
__local char localArray[16];
for(unsigned int index = 0; index < 16; ++index)
localArray[index] = 0;
input[0] = localArray[get_local_id(0)];
}
fatal error: error in backend: Cannot select:
0x5810cc0: i32,ch = load 0x57fa148,
0x5810ac0, 0x58105c0...
2010 Mar 25
1
Manually calculate SVM
Hi,
I'm learning more about SVMs and kernels in general. I've gotten used
to using the svm function in the e1071 package. It works great.
Now, I want to do/learn some more interesting stuff. (Perhaps my own
kernel and/or scoring system). So I want to better understand
1) how calculation of the kernel happens.
2) how to calculate the predicted value (y_hat) given a list of support