CO-HW1 - HackMD

###### tags: `Computer Organization` `computer organization` `thu` {%hackmd theme-dark %} # CO-HW1 ## Machine spec ![](https://i.imgur.com/kOAJQYC.png) ## Test result ![](https://i.imgur.com/lpocULQ.png) ![](https://i.imgur.com/kCYT70y.png) $$R_{peak} = n_{fpu} \cdot n_{cores} \cdot f$$ $$efficiency = \frac{Gflops}{R_{peak}} = \frac{93.818}{115.2}\approx 81.44\%$$ ## HPL.out v1 ``` ================================================================================ HPLinpack 2.3 -- High-Performance Linpack benchmark -- December 2, 2018 Written by A. Petitet and R. Clint Whaley, Innovative Computing Laboratory, UTK Modified by Piotr Luszczek, Innovative Computing Laboratory, UTK Modified by Julien Langou, University of Colorado Denver ================================================================================ An explanation of the input/output parameters follows: T/V : Wall time / encoded variant. N : The order of the coefficient matrix A. NB : The partitioning blocking factor. P : The number of process rows. Q : The number of process columns. Time : Time in seconds to solve the linear system. Gflops : Rate of execution for solving the linear system. The following parameter values will be used: N : 10000 NB : 88 108 128 168 188 PMAP : Row-major process mapping P : 2 Q : 2 PFACT : Left Crout Right NBMIN : 4 NDIV : 2 RFACT : Crout BCAST : 1ring DEPTH : 0 SWAP : Mix (threshold = 64) L1 : transposed form U : transposed form EQUIL : yes ALIGN : 8 double precision words -------------------------------------------------------------------------------- - The matrix A is randomly generated for each test. - The following scaled residual check will be computed: ||Ax-b||_oo / ( eps * ( || x ||_oo * || A ||_oo + || b ||_oo ) * N ) - The relative machine precision (eps) is taken to be 1.110223e-16 - Computational tests pass if scaled residuals are less than 16.0 ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 88 2 2 7.21 9.2530e+01 HPL_pdgesv() start time Mon Oct 3 17:47:41 2022 HPL_pdgesv() end time Mon Oct 3 17:47:48 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.42220796e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 88 2 2 7.19 9.2763e+01 HPL_pdgesv() start time Mon Oct 3 17:47:49 2022 HPL_pdgesv() end time Mon Oct 3 17:47:56 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.42220796e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 88 2 2 7.19 9.2776e+01 HPL_pdgesv() start time Mon Oct 3 17:47:57 2022 HPL_pdgesv() end time Mon Oct 3 17:48:04 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.75394366e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 108 2 2 7.24 9.2149e+01 HPL_pdgesv() start time Mon Oct 3 17:48:05 2022 HPL_pdgesv() end time Mon Oct 3 17:48:12 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.37582302e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 108 2 2 7.15 9.3273e+01 HPL_pdgesv() start time Mon Oct 3 17:48:13 2022 HPL_pdgesv() end time Mon Oct 3 17:48:20 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.37582302e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 108 2 2 7.15 9.3310e+01 HPL_pdgesv() start time Mon Oct 3 17:48:21 2022 HPL_pdgesv() end time Mon Oct 3 17:48:28 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.52455130e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 128 2 2 7.16 9.3090e+01 HPL_pdgesv() start time Mon Oct 3 17:48:29 2022 HPL_pdgesv() end time Mon Oct 3 17:48:36 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.91576596e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 128 2 2 7.16 9.3104e+01 HPL_pdgesv() start time Mon Oct 3 17:48:37 2022 HPL_pdgesv() end time Mon Oct 3 17:48:44 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.91576596e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 128 2 2 7.18 9.2910e+01 HPL_pdgesv() start time Mon Oct 3 17:48:45 2022 HPL_pdgesv() end time Mon Oct 3 17:48:52 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.86450164e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 168 2 2 7.80 8.5471e+01 HPL_pdgesv() start time Mon Oct 3 17:48:53 2022 HPL_pdgesv() end time Mon Oct 3 17:49:01 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.51145728e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 168 2 2 7.81 8.5399e+01 HPL_pdgesv() start time Mon Oct 3 17:49:02 2022 HPL_pdgesv() end time Mon Oct 3 17:49:10 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.51145728e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 168 2 2 7.80 8.5503e+01 HPL_pdgesv() start time Mon Oct 3 17:49:10 2022 HPL_pdgesv() end time Mon Oct 3 17:49:18 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.97913606e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 188 2 2 7.25 9.2030e+01 HPL_pdgesv() start time Mon Oct 3 17:49:19 2022 HPL_pdgesv() end time Mon Oct 3 17:49:26 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.90563662e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 188 2 2 7.24 9.2061e+01 HPL_pdgesv() start time Mon Oct 3 17:49:27 2022 HPL_pdgesv() end time Mon Oct 3 17:49:34 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.90563662e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 188 2 2 7.24 9.2063e+01 HPL_pdgesv() start time Mon Oct 3 17:49:35 2022 HPL_pdgesv() end time Mon Oct 3 17:49:43 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.65920119e-03 ...... PASSED ================================================================================ Finished 15 tests with the following results: 15 tests completed and passed residual checks, 0 tests completed and failed residual checks, 0 tests skipped because of illegal input values. -------------------------------------------------------------------------------- End of Tests. ================================================================================ ``` ## HPL.out v2 ``` ================================================================================ HPLinpack 2.3 -- High-Performance Linpack benchmark -- December 2, 2018 Written by A. Petitet and R. Clint Whaley, Innovative Computing Laboratory, UTK Modified by Piotr Luszczek, Innovative Computing Laboratory, UTK Modified by Julien Langou, University of Colorado Denver ================================================================================ An explanation of the input/output parameters follows: T/V : Wall time / encoded variant. N : The order of the coefficient matrix A. NB : The partitioning blocking factor. P : The number of process rows. Q : The number of process columns. Time : Time in seconds to solve the linear system. Gflops : Rate of execution for solving the linear system. The following parameter values will be used: N : 10000 NB : 88 108 128 168 188 PMAP : Row-major process mapping P : 2 Q : 2 PFACT : Left Crout Right NBMIN : 4 NDIV : 2 RFACT : Crout BCAST : 1ring DEPTH : 0 SWAP : Mix (threshold = 64) L1 : transposed form U : transposed form EQUIL : yes ALIGN : 8 double precision words -------------------------------------------------------------------------------- - The matrix A is randomly generated for each test. - The following scaled residual check will be computed: ||Ax-b||_oo / ( eps * ( || x ||_oo * || A ||_oo + || b ||_oo ) * N ) - The relative machine precision (eps) is taken to be 1.110223e-16 - Computational tests pass if scaled residuals are less than 16.0 ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 88 2 2 7.22 9.2365e+01 HPL_pdgesv() start time Mon Oct 3 23:18:34 2022 HPL_pdgesv() end time Mon Oct 3 23:18:41 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.42220796e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 88 2 2 7.17 9.2946e+01 HPL_pdgesv() start time Mon Oct 3 23:18:42 2022 HPL_pdgesv() end time Mon Oct 3 23:18:49 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.42220796e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 88 2 2 7.17 9.2970e+01 HPL_pdgesv() start time Mon Oct 3 23:18:50 2022 HPL_pdgesv() end time Mon Oct 3 23:18:57 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.75394366e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 108 2 2 7.11 9.3815e+01 HPL_pdgesv() start time Mon Oct 3 23:18:58 2022 HPL_pdgesv() end time Mon Oct 3 23:19:05 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.37582302e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 108 2 2 7.11 9.3818e+01 HPL_pdgesv() start time Mon Oct 3 23:19:06 2022 HPL_pdgesv() end time Mon Oct 3 23:19:13 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.37582302e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 108 2 2 7.11 9.3786e+01 HPL_pdgesv() start time Mon Oct 3 23:19:14 2022 HPL_pdgesv() end time Mon Oct 3 23:19:21 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.52455130e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 128 2 2 7.15 9.3252e+01 HPL_pdgesv() start time Mon Oct 3 23:19:22 2022 HPL_pdgesv() end time Mon Oct 3 23:19:29 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.91576596e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 128 2 2 7.15 9.3307e+01 HPL_pdgesv() start time Mon Oct 3 23:19:30 2022 HPL_pdgesv() end time Mon Oct 3 23:19:37 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.91576596e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 128 2 2 7.15 9.3252e+01 HPL_pdgesv() start time Mon Oct 3 23:19:38 2022 HPL_pdgesv() end time Mon Oct 3 23:19:45 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.86450164e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 168 2 2 7.69 8.6680e+01 HPL_pdgesv() start time Mon Oct 3 23:19:46 2022 HPL_pdgesv() end time Mon Oct 3 23:19:53 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.51145728e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 168 2 2 7.71 8.6453e+01 HPL_pdgesv() start time Mon Oct 3 23:19:54 2022 HPL_pdgesv() end time Mon Oct 3 23:20:02 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.51145728e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 168 2 2 7.69 8.6687e+01 HPL_pdgesv() start time Mon Oct 3 23:20:03 2022 HPL_pdgesv() end time Mon Oct 3 23:20:11 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.97913606e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2L4 10000 188 2 2 7.21 9.2501e+01 HPL_pdgesv() start time Mon Oct 3 23:20:11 2022 HPL_pdgesv() end time Mon Oct 3 23:20:19 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.90563662e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2C4 10000 188 2 2 7.21 9.2548e+01 HPL_pdgesv() start time Mon Oct 3 23:20:19 2022 HPL_pdgesv() end time Mon Oct 3 23:20:27 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.90563662e-03 ...... PASSED ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR00C2R4 10000 188 2 2 7.21 9.2513e+01 HPL_pdgesv() start time Mon Oct 3 23:20:27 2022 HPL_pdgesv() end time Mon Oct 3 23:20:35 2022 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 2.65920119e-03 ...... PASSED ================================================================================ Finished 15 tests with the following results: 15 tests completed and passed residual checks, 0 tests completed and failed residual checks, 0 tests skipped because of illegal input values. -------------------------------------------------------------------------------- End of Tests. ================================================================================ ```