GPGPU-Sim PTX: pushing kernel '_Z20Convolution2D_kernelPfS_' to stream 0, gridDim= (4096,1,1) blockDim = (1024,1,1) 
gpu_sim_cycle = 596345
gpu_ipc =     435.5220
total_dl1_misses=405108
total_dl1_accesses=1951884
total_dl1_miss_rate= 0.207547
gpgpu_stall_shd_mem[gl_mem][coal_stall] = 1045718
L2 Cache Total Miss Rate = 0.489
