GPGPU-Sim PTX: pushing kernel '_Z20convolution3D_kernelPfS_i' to stream 0, gridDim= (1024,1,1) blockDim = (1024,1,1) 
gpu_sim_cycle = 350926
gpu_ipc =     259.2556
total_dl1_misses=329866
total_dl1_accesses=613200
total_dl1_miss_rate= 0.537942
gpgpu_stall_shd_mem[gl_mem][coal_stall] = 1293128
L2 Cache Total Miss Rate = 0.361
