under test, not sure no errors

upstream_ref/sgemm_cuda/1_naive.cuh

@@ -0,0 +1,29 @@
+#pragma once
+
+#include <cstdio>
+#include <cstdlib>
+#include <cublas_v2.h>
+#include <cuda_runtime.h>
+
+/*
+
+Matrix sizes:
+MxK * KxN = MxN
+
+*/
+
+__global__ void sgemm_naive(int M, int N, int K, float alpha, const float *A,
+                            const float *B, float beta, float *C) {
+  const uint x = blockIdx.x * blockDim.x + threadIdx.x;
+  const uint y = blockIdx.y * blockDim.y + threadIdx.y;
+
+  // if statement is necessary to make things work under tile quantization
+  if (x < M && y < N) {
+    float tmp = 0.0;
+    for (int i = 0; i < K; ++i) {
+      tmp += A[x * K + i] * B[i * N + y];
+    }
+    // C = α*(A@B)+β*C
+    C[x * N + y] = alpha * tmp + beta * C[x * N + y];
+  }
+}