data: cat SGEMM files from 3 repos into cat_files/

siboehm/SGEMM_CUDA (19 files):
  siboehm_sgemm.cu, siboehm_runner.cu, siboehm_runner.cuh, siboehm_kernels.cuh
  siboehm_cuBLAS_sgemm.cu, siboehm_simplest_kernel.cu, siboehm_CMakeLists.txt
  siboehm_{1_naive..12_kernel_double_buffering}.cuh

wangzyon/NVIDIA_SGEMM_PRACTICE (12 files):
  wangzyon_sgemm.cu, wangzyon_utils.cu, wangzyon_utils.cuh, wangzyon_kernel.cuh
  wangzyon_CMakeLists.txt, wangzyon_kernel_{1..7}.cuh

edtallison/sgemm-cuda (19 files):
  edtallison_sgemm.cu, edtallison_runner.cu, edtallison_runner.cuh
  edtallison_kernels.cuh, edtallison_cuBLAS_sgemm.cu, edtallison_simplest_kernel.cu
  edtallison_CMakeLists.txt, edtallison_{01_naive..12_kernel_double_buffering}.cuh

cat_files/ total: 25 → 75 files

cat_files/siboehm_runner.cuh

@@ -0,0 +1,26 @@
+#pragma once
+#include <cublas_v2.h>
+#include <cuda_runtime.h>
+#include <fstream>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <time.h>
+#include <unistd.h>
+
+void cudaCheck(cudaError_t error, const char *file,
+               int line); // CUDA error check
+void CudaDeviceInfo();    // print CUDA information
+
+void range_init_matrix(float *mat, int N);
+void randomize_matrix(float *mat, int N);
+void zero_init_matrix(float *mat, int N);
+void copy_matrix(const float *src, float *dest, int N);
+void print_matrix(const float *A, int M, int N, std::ofstream &fs);
+bool verify_matrix(float *mat1, float *mat2, int N);
+
+float get_current_sec();                        // Get the current moment
+float cpu_elapsed_time(float &beg, float &end); // Calculate time difference
+
+void run_kernel(int kernel_num, int m, int n, int k, float alpha, float *A,
+                float *B, float beta, float *C, cublasHandle_t handle);