AVX Extensions - Ongoing development?
Message boards :
Number crunching :
AVX Extensions - Ongoing development?
Message board moderation
Previous · 1 . . . 4 · 5 · 6 · 7
| Author | Message |
|---|---|
|
Orioneti Send message Joined: 22 Oct 07 Posts: 21 Credit: 23,642,634 RAC: 0 
|
2600k@4488Mhz w7sp1 ...
Ftst_v7_J45 started.
Optimal function choices:
--------------------------------------------------------
name timing error
--------------------------------------------------------
v_BaseLineSmooth (no other)
v_GetPowerSpectrum 0.000089 0.00000 test
v_vGetPowerSpectrum 0.000044 0.00000 test
v_vGetPowerSpectrum2 0.000054 0.00000 test
v_vGetPowerSpectrumUnrolled 0.000041 0.00000 test
v_vGetPowerSpectrumUnrolled2 0.000056 0.00000 test
v_avxGetPowerSpectrum 0.000037 0.00000 test
v_avxGetPowerSpectrum 0.000037 0.00000 choice
v_ChirpData 0.003751 0.00000 test
fpu_ChirpData 0.008935 0.00000 test
fpu_opt_ChirpData 0.003708 0.00000 test
v_vChirpData_x86_64 0.043466 0.00000 test
sse1_ChirpData_ak 0.005292 0.00000 test
sse1_ChirpData_ak8e 0.004292 0.00000 test
sse1_ChirpData_ak8h 0.004518 0.00000 test
sse2_ChirpData_ak 0.004998 0.00000 test
sse2_ChirpData_ak8 0.003289 0.00000 test
sse3_ChirpData_ak 0.004819 0.00000 test
sse3_ChirpData_ak8 0.003247 0.00000 test
avx_ChirpData_a 0.001538 0.00000 test
avx_ChirpData_b 0.001720 0.00000 test
avx_ChirpData_c 0.001547 0.00000 test
avx_ChirpData_d 0.001439 0.00000 test
avx_ChirpData_d 0.001439 0.00000 choice
v_Transpose 0.002295 0.00000 test
v_Transpose2 0.002469 0.00000 test
v_Transpose4 0.001244 0.00000 test
v_Transpose8 0.002225 0.00000 test
v_pfTranspose2 0.001383 0.00000 test
v_pfTranspose4 0.001181 0.00000 test
v_pfTranspose8 0.002386 0.00000 test
v_vTranspose4 0.000728 0.00000 test
v_vTranspose4np 0.000984 0.00000 test
v_vTranspose4ntw 0.006246 0.00000 test
v_vTranspose4x8ntw 0.002533 0.00000 test
v_vTranspose4x16ntw 0.000708 0.00000 test
v_vpfTranspose8x4ntw 0.006067 0.00000 test
v_avxTranspose4x8ntw 0.002625 0.00000 test
v_avxTranspose4x16ntw 0.000612 0.00000 test
v_avxTranspose8x4ntw 0.006264 0.00000 test
v_avxTranspose8x8ntw_a 0.001964 0.00000 test
v_avxTranspose8x8ntw_b 0.002406 0.00000 test
v_avxTranspose4x16ntw 0.000612 0.00000 choice
FPU opt folding 0.001707 0.00000 test
AK SSE folding 0.000374 0.00000 test
BH SSE folding 0.000357 0.00000 test
JS AVX_a folding 0.000314 0.00000 test
JS AVX_c folding 0.000319 0.00000 test
JS AVX_a folding 0.000314 0.00000 choice
Test duration 3.01 seconds
2600k@stock w7sp1 ...
Ftst_v7_J45 started.
Optimal function choices:
--------------------------------------------------------
name timing error
--------------------------------------------------------
v_BaseLineSmooth (no other)
v_GetPowerSpectrum 0.000114 0.00000 test
v_vGetPowerSpectrum 0.000057 0.00000 test
v_vGetPowerSpectrum2 0.000069 0.00000 test
v_vGetPowerSpectrumUnrolled 0.000052 0.00000 test
v_vGetPowerSpectrumUnrolled2 0.000072 0.00000 test
v_avxGetPowerSpectrum 0.000047 0.00000 test
v_avxGetPowerSpectrum 0.000047 0.00000 choice
v_ChirpData 0.004174 0.00000 test
fpu_ChirpData 0.011399 0.00000 test
fpu_opt_ChirpData 0.004132 0.00000 test
v_vChirpData_x86_64 0.055563 0.00000 test
sse1_ChirpData_ak 0.006768 0.00000 test
sse1_ChirpData_ak8e 0.005486 0.00000 test
sse1_ChirpData_ak8h 0.005763 0.00000 test
sse2_ChirpData_ak 0.006365 0.00000 test
sse2_ChirpData_ak8 0.004205 0.00000 test
sse3_ChirpData_ak 0.006157 0.00000 test
sse3_ChirpData_ak8 0.004132 0.00000 test
avx_ChirpData_a 0.001956 0.00000 test
avx_ChirpData_b 0.002194 0.00000 test
avx_ChirpData_c 0.001969 0.00000 test
avx_ChirpData_d 0.001815 0.00000 test
avx_ChirpData_d 0.001815 0.00000 choice
v_Transpose 0.002897 0.00000 test
v_Transpose2 0.003133 0.00000 test
v_Transpose4 0.001580 0.00000 test
v_Transpose8 0.002816 0.00000 test
v_pfTranspose2 0.001655 0.00000 test
v_pfTranspose4 0.001482 0.00000 test
v_pfTranspose8 0.002997 0.00000 test
v_vTranspose4 0.000878 0.00000 test
v_vTranspose4np 0.001245 0.00000 test
v_vTranspose4ntw 0.007768 0.00000 test
v_vTranspose4x8ntw 0.003076 0.00000 test
v_vTranspose4x16ntw 0.000856 0.00000 test
v_vpfTranspose8x4ntw 0.007466 0.00000 test
v_avxTranspose4x8ntw 0.003220 0.00000 test
v_avxTranspose4x16ntw 0.000735 0.00000 test
v_avxTranspose8x4ntw 0.007752 0.00000 test
v_avxTranspose8x8ntw_a 0.002395 0.00000 test
v_avxTranspose8x8ntw_b 0.002921 0.00000 test
v_avxTranspose4x16ntw 0.000735 0.00000 choice
FPU opt folding 0.002181 0.00000 test
AK SSE folding 0.000479 0.00000 test
BH SSE folding 0.000458 0.00000 test
JS AVX_a folding 0.000402 0.00000 test
JS AVX_c folding 0.000408 0.00000 test
JS AVX_a folding 0.000402 0.00000 choice
Test duration 3.77 seconds
Ftst_v7 completed successfully.
ID: 1108599 ·  |
|
Stewart Send message Joined: 28 Aug 07 Posts: 4 Credit: 829,029 RAC: 0 
|
i5-2500K at 4.4GHz, Win7 SP1 =========================================================
Ftst_v7_J45 started.
Optimal function choices:
--------------------------------------------------------
name timing error
--------------------------------------------------------
v_BaseLineSmooth (no other)
v_GetPowerSpectrum 0.000090 0.00000 test
v_vGetPowerSpectrum 0.000045 0.00000 test
v_vGetPowerSpectrum2 0.000054 0.00000 test
v_vGetPowerSpectrumUnrolled 0.000042 0.00000 test
v_vGetPowerSpectrumUnrolled2 0.000057 0.00000 test
v_avxGetPowerSpectrum 0.000037 0.00000 test
v_avxGetPowerSpectrum 0.000037 0.00000 choice
v_ChirpData 0.003710 0.00000 test
fpu_ChirpData 0.009046 0.00000 test
fpu_opt_ChirpData 0.003696 0.00000 test
v_vChirpData_x86_64 0.044385 0.00000 test
sse1_ChirpData_ak 0.005062 0.00000 test
sse1_ChirpData_ak8e 0.004202 0.00000 test
sse1_ChirpData_ak8h 0.004348 0.00000 test
sse2_ChirpData_ak 0.004942 0.00000 test
sse2_ChirpData_ak8 0.003118 0.00000 test
sse3_ChirpData_ak 0.004789 0.00000 test
sse3_ChirpData_ak8 0.003079 0.00000 test
avx_ChirpData_a 0.001561 0.00000 test
avx_ChirpData_b 0.001532 0.00000 test
avx_ChirpData_c 0.001575 0.00000 test
avx_ChirpData_d 0.001451 0.00000 test
avx_ChirpData_d 0.001451 0.00000 choice
v_Transpose 0.002687 0.00000 test
v_Transpose2 0.002578 0.00000 test
v_Transpose4 0.001341 0.00000 test
v_Transpose8 0.002378 0.00000 test
v_pfTranspose2 0.001668 0.00000 test
v_pfTranspose4 0.001475 0.00000 test
v_pfTranspose8 0.002782 0.00000 test
v_vTranspose4 0.000911 0.00000 test
v_vTranspose4np 0.001079 0.00000 test
v_vTranspose4ntw 0.006266 0.00000 test
v_vTranspose4x8ntw 0.002541 0.00000 test
v_vTranspose4x16ntw 0.000748 0.00000 test
v_vpfTranspose8x4ntw 0.006083 0.00000 test
v_avxTranspose4x8ntw 0.002636 0.00000 test
v_avxTranspose4x16ntw 0.000676 0.00000 test
v_avxTranspose8x4ntw 0.006290 0.00000 test
v_avxTranspose8x8ntw_a 0.002008 0.00000 test
v_avxTranspose8x8ntw_b 0.002421 0.00000 test
v_avxTranspose4x16ntw 0.000676 0.00000 choice
FPU opt folding 0.001742 0.00000 test
AK SSE folding 0.000382 0.00000 test
BH SSE folding 0.000364 0.00000 test
JS AVX_a folding 0.000319 0.00000 test
JS AVX_c folding 0.000325 0.00000 test
JS AVX_a folding 0.000319 0.00000 choice
Test duration 3.07 seconds
Ftst_v7 completed successfully.ID: 1109215 · |
Ivailo Bonev  Send message Joined: 26 Jun 00 Posts: 247 Credit: 35,864,461 RAC: 2 
|
I don't know are there any development efforts now, but I find interesting document about AVX extensions on Intel web site: Intel Advanced Vector Extensions Programming Reference (June 2011) (pdf). Hope it helps :) 
ID: 1124242 · |
 Fred J. Verster  Send message Joined: 21 Apr 04 Posts: 3252 Credit: 31,903,643 RAC: 0 
|
Nice info on AVX, with 595 pages, this can take awhile ;-) . But certainly worthwhile reading. 
ID: 1124244 · |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.