GPGPU-Sim PTX: pushing kernel '_Z20convolution3D_kernelPfS_i' to stream 0, gridDim= (1024,1,1) blockDim = (1024,1,1) 
gpu_sim_cycle = 266656
gpu_ipc =     341.1870
total_dl1_misses=325554
total_dl1_accesses=613200
total_dl1_miss_rate= 0.530910
gpgpu_stall_shd_mem[gl_mem][coal_stall] = 912320
L2 Cache Total Miss Rate = 0.366
