SOURCE: linpackc BUILD: cc -DDP -DUNROLL -Xa -dalign linpackc.c -o linpackcdb -lm -xcache=64/64/2:5120/256/10 -m64
————————————————————————————————
A 0, 16 1800 32.0 US-IV+ 2.4
./linpackcdb Unrolled Double Precision Linpack Unrolled Double Precision Linpack NTIMES= 1000 norm. resid resid machep x[0]-1 x[n-1]-1 1.7 7.41628980e-14 2.22044605e-16 -1.49880108e-14 -1.89848137e-14 times are reported for matrices of order 100 dgefa dgesl total kflops unit ratio times for array with leading dimension of 201 0.00 0.00 0.00 215459 0.01 0.06 0.00 0.00 0.00 217575 0.01 0.06 0.00 0.00 0.00 218267 0.01 0.06 0.00 0.00 0.00 217998 0.01 0.06 times for array with leading dimension of 200 0.00 0.00 0.00 218823 0.01 0.06 0.00 0.00 0.00 221220 0.01 0.06 0.00 0.00 0.00 221505 0.01 0.06 0.00 0.00 0.00 220783 0.01 0.06 Unrolled Double Precision 217998 Kflops ; 1000 Reps 217998 x 8 CPU's= 1,743,984 Kflops
————————————————————————————————
SPARC64-VII mode
cc -DDP -DUNROLL -Xa -dalign linpackc.c -o linpackcdb -lm -xcache=64/64/2:5120/256/10 -m64 Precision Linpack Unrolled Double Precision Linpack NTIMES= 1000 times for array with leading dimension of 200 0.00 0.00 0.00 321172 0.01 0.04 0.00 0.00 0.00 320274 0.01 0.04 0.00 0.00 0.00 319083 0.01 0.04 0.00 0.00 0.00 323038 0.01 0.04 Unrolled Double Precision 323038 Kflops ; 1000 Reps
16 CPU's * 323038 = 5,168,608 Kflops
———————————–
A 0 900 8.0 US-III+ 2.3
Unrolled Double Precision Linpack NTIMES= 1000 norm. resid resid machep x[0]-1 x[n-1]-1 1.7 7.41628980e-14 2.22044605e-16 -1.49880108e-14 -1.89848137e-14 times are reported for matrices of order 100 dgefa dgesl total kflops unit ratio Unrolled Double Precision 110142 Kflops ; 1000 Reps times for array with leading dimension of 200 0.01 0.00 0.01 111345 0.02 0.11 0.01 0.00 0.01 107108 0.02 0.11 0.01 0.00 0.01 106858 0.02 0.11 0.01 0.00 0.01 110220 0.02 0.11 Unrolled Double Precision 108042 Kflops ; 1000 Reps
8CPU's *108042 = 864,336 Kflops
——————————————————-
0 1000 MHz SUNW,UltraSPARC-T1 on-line
./linpackcdb Unrolled Double Precision Linpack NTIMES= 1000 norm. resid resid machep x[0]-1 x[n-1]-1 1.7 7.41628980e-14 2.22044605e-16 -1.49880108e-14 -1.89848137e-14 times are reported for matrices of order 100 times for array with leading dimension of 200 0.16 0.00 0.16 4227 0.47 2.90 0.16 0.00 0.16 4225 0.47 2.90 0.16 0.00 0.16 4215 0.47 2.91 0.15 0.00 0.16 4383 0.46 2.80 Unrolled Double Precision 4303 Kflops ; 1000 Reps
24 Threads * 4303 Kflops = 103,272 Kflops
_________________________________________________
gcc -DDP -DUNROLL -dalign linpackc.c -o linpackcdb -lm -m64
Quad-Core AMD Opteron(tm) Processor 2352
vendor: Hynix Semiconductor (Hyundai Electronics)
physical id: 4
bus info: cpu@0
slot: CPU socket #0
size: 2100MHz
capacity: 4230MHz
width: 64 bits
Unrolled Double Precision Linpack times are reported for matrices of order 100 dgefa dgesl total kflops unit ratio times for array with leading dimension of 201 Unrolled Double Precision Linpack 0.00 0.00 0.00 228965 0.01 0.05 times are reported for matrices of order 100
times for array with leading dimension of 200 0.00 0.00 0.00 228889 0.01 0.05 0.00 0.00 0.00 343333 0.01 0.04 0.00 0.00 0.00 343505 0.01 0.04 0.00 0.00 0.00 269428 0.01 0.05 Unrolled Double Precision 267330 Kflops ; 1000 Reps 8 THREADS * 267330 Kflops = 2,138,640 ---------------------------------------------
blade T6320
0 1415 MHz SUNW,UltraSPARC-T2 on-line
Unrolled Double Precision Linpack times are reported for matrices of order 100 dgefa dgesl total kflops unit ratio times for array with leading dimension of 201 0.01 0.00 0.02 45674 0.04 0.27 0.01 0.00 0.01 45952 0.04 0.27 0.01 0.00 0.02 45342 0.04 0.27 0.01 0.00 0.01 49138 0.04 0.25 Unrolled Double Precision 44945 Kflops ; 1000 Reps
64 Threads x 45342 = 2,901,888
————————————————————————————
Mac OX 10.6.7
CPU: 2.16 GHZ Intel Core 2 Duo
gcc -DDP -DUNROLL -dalign linpackcmac.c -o linpackcdb -lm -fnested-functions -m64 $ Unrolled Double Precision Linpack NTIMES= 1000 norm. resid resid machep x[0]-1 x[n-1]-1 1.7 7.41628980e-14 2.22044605e-16 -1.49880108e-14 -1.89848137e-14 times are reported for matrices of order 100 times for array with leading dimension of 200 0.00 0.00 0.00 319231 0.01 0.04 0.00 0.00 0.00 325434 0.01 0.04 0.00 0.00 0.00 318639 0.01 0.04 0.00 0.00 0.00 329319 0.01 0.04 Unrolled Double Precision 310696 Kflops ; 1000 Reps 318639 x 2 CPUs = 637,278 Kflops
————————————————————————————
Mac OX 10.6.7
CPU: 2.0 GHZ Intel Core 2 Duo
Cmini
Unrolled Double Precision Linpack
NTIMES= 1000
norm. resid resid machep x[0]-1 x[n-1]-1
1.7 7.41628980e-14 2.22044605e-16 -1.49880108e-14 -1.89848137e-14
times are reported for matrices of order 100
dgefa dgesl total kflops unit ratio
times for array with leading dimension of 201
0.00 0.00 0.00 282812 0.01 0.04
0.00 0.00 0.00 281767 0.01 0.04
0.00 0.00 0.00 282695 0.01 0.04
0.00 0.00 0.00 284255 0.01 0.04
times for array with leading dimension of 200
0.00 0.00 0.00 288273 0.01 0.04
0.00 0.00 0.00 290714 0.01 0.04
0.00 0.00 0.00 289001 0.01 0.04
0.00 0.00 0.00 290686 0.01 0.04
Unrolled Double Precision 284255 Kflops ; 1000 Reps
2 cpus * 284255 = 568,510 Kflops