killeent

#include "TH.h"
#include "THC.h"
#include <cstdio>
#include "sys/time.h"
#include <vector>
#include "cuda_profiler_api.h"

const long loops = 10;

void compare(THIntTensor *input, THIntTensor *mode, THLongTensor *indices,

killeent

local runtests = false
if not cutorch then
   require 'cutorch'
   runtests = true
end

local test = {}
local minsize = 5
local maxsize = 10
local minvalue = 2

killeent

#ifndef THC_GENERIC_FILE
#define THC_GENERIC_FILE "generic/THCTensorMode.cu"
#else

THC_API void THCTensor_(calculateMode)(THCState *state,
                                        THCTensor *values,
                                        THCudaLongTensor *indices,
                                        THCTensor *input,
                                        THCudaLongStorage *sortBuffer,
                                        int dimension,

killeent

#ifndef THC_TENSOR_MODE_CUH
#define THC_TENSOR_MODE_CUH

#include "THCNumerics.cuh"
#include "THCSortUtils.cuh"

struct ThrustHalfLess
{
  __host__ __device__ inline bool operator()(const half& lhs, const half& rhs) {
    return THCNumerics<half>::lt(lhs, rhs);

killeent

Sum of	10	trials used to generate results	
----------------------------------------------------------------	
CatArray for	2	size	1	1D Tensors took	0.00029397010803223	seconds.	
CatArray for	4	size	1	1D Tensors took	0.00024986267089844	seconds.	
CatArray for	8	size	1	1D Tensors took	0.00025296211242676	seconds.	
CatArray for	32	size	1	1D Tensors took	0.00030803680419922	seconds.	
CatArray for	128	size	1	1D Tensors took	0.00056195259094238	seconds.	
CatArray for	512	size	1	1D Tensors took	0.0013229846954346	seconds.	
CatArray for	1024	size	1	1D Tensors took	0.0022039413452148	seconds.	
CatArray for	2048	size	1	1D Tensors took	0.004547119140625	seconds.	

killeent

----------------------------------------------------------------	
Soumith's Benchmarks (The times are the sum of	5	trials)	
----------------------------------------------------------------	
ms: 0.066048
ms: 0.028448
ms: 0.027008
ms: 0.026304
ms: 0.026624
CatArray for 32 1x600 Tensors along dim=1 took	7.6389312744141e-05	seconds	
ms: 0.041856

killeent

Sum of	10	trials used to generate results	
----------------------------------------------------------------	
CatArray for	2	size	1	1D Tensors took	0.0005650520324707	seconds.	
CatArray for	4	size	1	1D Tensors took	0.00078177452087402	seconds.	
CatArray for	8	size	1	1D Tensors took	0.0015158653259277	seconds.	
CatArray for	32	size	1	1D Tensors took	0.0047669410705566	seconds.	
CatArray for	128	size	1	1D Tensors took	0.021991968154907	seconds.	
CatArray for	512	size	1	1D Tensors took	0.079319953918457	seconds.	
CatArray for	1024	size	1	1D Tensors took	0.15872097015381	seconds.	
CatArray for	2048	size	1	1D Tensors took	0.30642604827881	seconds.	

killeent

----------------------------------------------------------------	
Soumith's Benchmarks (The times are the sum of	5	trials)	
----------------------------------------------------------------	
ms: 0.280992
ms: 0.218592
ms: 0.218208
ms: 0.253888
ms: 0.243072
CatArray for 32 1x600 Tensors along dim=1 took	0.00028080940246582	seconds	
ms: 0.898176

killeent

Sum of	10	trials used to generate results	
----------------------------------------------------------------	
CatArray for	2	size	1	1D Tensors took	0.00030994415283203	seconds.	
CatArray for	4	size	1	1D Tensors took	0.00022506713867188	seconds.	
CatArray for	8	size	1	1D Tensors took	0.00023889541625977	seconds.	
CatArray for	32	size	1	1D Tensors took	0.00027704238891602	seconds.	
CatArray for	128	size	1	1D Tensors took	0.00044894218444824	seconds.	
CatArray for	512	size	1	1D Tensors took	0.0012199878692627	seconds.	
CatArray for	1024	size	1	1D Tensors took	0.0020511150360107	seconds.	
CatArray for	2048	size	1	1D Tensors took	0.0042030811309814	seconds.	

killeent

Sum of	10	trials used to generate results	
----------------------------------------------------------------	
CatArray for	2	size	1	1D Tensors took	0.00037097930908203	seconds.	
CatArray for	4	size	1	1D Tensors took	0.00036001205444336	seconds.	
CatArray for	8	size	1	1D Tensors took	0.00064897537231445	seconds.	
CatArray for	32	size	1	1D Tensors took	0.0023789405822754	seconds.	
CatArray for	128	size	1	1D Tensors took	0.0089218616485596	seconds.	
CatArray for	512	size	1	1D Tensors took	0.036385059356689	seconds.	
CatArray for	1024	size	1	1D Tensors took	0.075536012649536	seconds.	
CatArray for	2048	size	1	1D Tensors took	0.14832401275635	seconds.