grid is 1 x 1 Sequential: 0.448263 secs (40.155 GFlop/s) Root waited for 3.833e-06 seconds Populate root node: 0.0179127 secs Spread from root: 0.0249761 secs [MC,* ] AllGather: 0.00112518 secs (2730.23 MB/s) for3000 x 128 local matrix [* ,MR] AllGather: 0.00285713 secs (1075.2 MB/s) for 128 x 3000 local matrix Local gemm: 0.0595011 secs (38.722 GFlop/s) for 3000 x 3000 x 128 product [MC,* ] AllGather: 0.000799896 secs (3840.5 MB/s) for3000 x 128 local matrix [* ,MR] AllGather: 0.00229768 secs (1337 MB/s) for 128 x 3000 local matrix Local gemm: 0.0541277 secs (42.566 GFlop/s) for 3000 x 3000 x 128 product [MC,* ] AllGather: 0.000855213 secs (3592.09 MB/s) for3000 x 128 local matrix [* ,MR] AllGather: 0.00181724 secs (1690.48 MB/s) for 128 x 3000 local matrix Local gemm: 0.0595224 secs (38.7081 GFlop/s) for 3000 x 3000 x 128 product [MC,* ] AllGather: 0.000881357 secs (3485.53 MB/s) for3000 x 128 local matrix [* ,MR] AllGather: 0.00179303 secs (1713.3 MB/s) for 128 x 3000 local matrix Local gemm: 0.0541061 secs (42.583 GFlop/s) for 3000 x 3000 x 128 product [MC,* ] AllGather: 0.000873216 secs (3518.03 MB/s) for3000 x 128 local matrix [* ,MR] AllGather: 0.00232613 secs (1320.65 MB/s) for 128 x 3000 local matrix Local gemm: 0.0586013 secs (39.3165 GFlop/s) for 3000 x 3000 x 128 product [MC,* ] AllGather: 0.000887813 secs (3460.19 MB/s) for3000 x 128 local matrix [* ,MR] AllGather: 0.00178803 secs (1718.09 MB/s) for 128 x 3000 local matrix Local gemm: 0.0595247 secs (38.7066 GFlop/s) for 3000 x 3000 x 128 product [MC,* ] AllGather: 0.000860281 secs (3570.93 MB/s) for3000 x 128 local matrix [* ,MR] AllGather: 0.00184091 secs (1668.74 MB/s) for 128 x 3000 local matrix Local gemm: 0.0542341 secs (42.4825 GFlop/s) for 3000 x 3000 x 128 product [MC,* ] AllGather: 0.000707623 secs (3527.3 MB/s) for3000 x 104 local matrix [* ,MR] AllGather: 0.00150543 secs (1658 MB/s) for 104 x 3000 local matrix Local gemm: 0.0498551 secs (37.5488 GFlop/s) for 3000 x 3000 x 104 product Distributed Gemm: 0.484105 secs Gathered to root: 0.0242319 secs