GPGPU-Sim PTX: pushing kernel '_Z11gemm_kernelPfS_S_' to stream 0, gridDim= (1024,1,1) blockDim = (1024,1,1) 
gpu_sim_cycle = 40481116
gpu_ipc =     266.4366
total_dl1_misses=33619968
total_dl1_accesses=67141632
total_dl1_miss_rate= 0.500732
gpgpu_stall_shd_mem[gl_mem][coal_stall] = 36178983
L2 Cache Total Miss Rate = 0.075
