On Thursday 12 March 2009 14:23:35 Jeff Gilchrist wrote: > On Thu, Mar 12, 2009 at 10:20 AM, Cactus <rieman...@googlemail.com> wrote: > > This can happen when tune cannot get a stable result. > > Does it fail consistently at the same point? > > Yes, I just ran it about 6 times and it always fails after it displays > the #define GCDEXT_THRESHOLD line. There system is not loaded either > so I'm not sure what is going on.
for tuneup/speed try adjusting the precision -p 10000 was the old precision , it wont be so fussy about jitters > > Also some strange results with this 32bit window binary with > run-speed.py. I noticed you had x64\ directory hard-coded into the > script, is it only intended for 64bit code? > > Machine: x86 Family 6 Model 15 Stepping 6, GenuineIntel > Running: Windows-Vista-6.0.6001-SP1 > SPEED CURVE FIT cycles = c[0] + c[1] * no_of_limbs + c[2] * no_of_limbs^2 > ROUTINE c[0] c[1] c[2] > mpn_add_n 20.48 4.13 -0.00 > mpn_addadd_n failed to parse output > mpn_addsub_n failed to parse output > mpn_addlsh1_n failed to parse output > mpn_com_n 7.57 2.13 -0.00 > mpn_divexact_1.333 16.63 10.34 -0.00 > mpn_lshift.33 19.15 1.34 -0.00 > mpn_divrem_1.3333 -30.76 41.44 -0.00 > mpn_addmul_1.3333 18.23 5.15 -0.00 > mpn_lshift1 17.97 1.35 -0.00 > mpn_modexact_1_odd.333 29.91 10.08 0.00 > mpn_mod_1.3333 -31.35 41.43 -0.00 > MPN_COPY 89.13 0.81 0.00 > mpn_mul_1.3333 24.37 3.60 -0.00 > noop 5.99 0.00 -0.00 > mpn_rshift1 17.60 1.33 -0.00 > mpn_rshift.33 18.58 1.34 -0.00 > mpn_sub_n 23.32 3.59 -0.00 > mpn_submul_1.3333 16.38 6.16 -0.00 > mpn_sublsh1_n failed to parse output > mpn_sumdiff_n failed to parse output > count_leading_zeros 4.47 0.00 -0.00 > gmp_allocate_free 327.11 -0.01 0.00 > malloc_realloc_free 1457.05 -2.48 0.00 > gmp_allocate_reallocate_free 722.33 -0.02 0.00 > mpn_dc_divrem_n -15352.67 538.80 2.89 > mpn_dc_divrem_sb 1585.08 35.94 6.27 > malloc_free 463.55 -0.91 0.00 > mpn_dc_tdiv_qr -14885.74 557.67 2.84 > mpn_kara_mul_n -16990.40 435.25 0.97 > mpn_kara_sqr_n -12886.33 316.65 0.69 > mpn_mul_basecase -2729.78 45.12 4.98 > mpn_mul_fft_full -526633.57 2293.79 -0.01 > mpn_mul_n -19624.42 501.12 0.66 > mpn_sqr_basecase -1602.29 34.75 2.51 > mpn_sqr_n -14716.82 361.48 0.51 > mpn_toom3_mul_n -30056.98 564.75 0.54 > mpn_toom3_sqr_n -22064.54 404.30 0.43 > mpn_umul_ppmm 14.64 0.00 -0.00 > mpz_add 62.63 4.08 -0.00 > mpz_init_realloc_clear 1403.25 -2.14 0.00 > mpz_init_clear 341.98 0.01 -0.00 > mpz_powm 27870.72 6756.92 1964.00 > udiv_qrnnd 51.57 -0.00 0.00 > udiv_qrnnd_c 88.59 0.00 -0.00 > udiv_qrnnd_preinv1 29.45 0.00 -0.00 > udiv_qrnnd_preinv2 35.10 0.00 -0.00 > umul_ppmm 4.92 -0.00 0.00 > > > Jeff. > > --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "mpir-devel" group. To post to this group, send email to mpir-devel@googlegroups.com To unsubscribe from this group, send email to mpir-devel+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/mpir-devel?hl=en -~----------~----~----~----~------~----~------~--~---