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/wangzyon_kernel_1.cuh

@@ -0,0 +1,19 @@
+#pragma once
+
+#include <cuda_runtime.h>
+#include <cublas_v2.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+__global__ __launch_bounds__(1024) void
+mysgemm_v1(int M, int N, int K, float alpha, float *A, float *B, float beta, float *C) {
+
+    int gx = blockIdx.x * blockDim.x + threadIdx.x; // 全局x
+    int gy = blockIdx.y * blockDim.y + threadIdx.y; // 全局y
+
+    float tmp = 0.;
+    for (int i = 0; i < K; i++) {
+        tmp += A[gy * K + i] * B[i * N + gx]; // 两次全局内存访问和一次FMA（累加乘）
+    }
+    C[gy * N + gx] = alpha * tmp + beta * C[gy * N + gx];
+}