Forum > GPU crunching

GPU client

<< < (7/47) > >>

Radiohead:
New data with new 169.21 videodrivers.

[attachment deleted by admin]

Devaster:
HEY YA !

this version produces correct results with small differences
this is from cuda app :

--- Code: ---<best_spike>
  <peak_power>22.561671618532</peak_power>
  <mean_power>1</mean_power>
  <time>2451239.5780686</time>
  <ra>8.3192064227348</ra>
  <decl>27.898178773406</decl>
  <q_pix>0</q_pix>
  <freq>1418974011.7011</freq>
  <detection_freq>1418983759.2021</detection_freq>
  <barycentric_freq>0</barycentric_freq>
  <fft_len>131072</fft_len>
  <chirp_rate>-0.90022989063243</chirp_rate>
  <rfi_checked>0</rfi_checked>
  <rfi_found>0</rfi_found>
  <reserved>0</reserved>
</best_spike>
--- End code ---

and this is from default app :

--- Code: ---<best_spike>
  <peak_power>22.561794281006</peak_power>
  <mean_power>1</mean_power>
  <time>2451239.5780686</time>
  <ra>8.3192064227348</ra>
  <decl>27.898178773406</decl>
  <q_pix>0</q_pix>
  <freq>1418975203.0489</freq>
  <detection_freq>1418975184.9249</detection_freq>
  <barycentric_freq>0</barycentric_freq>
  <fft_len>131072</fft_len>
  <chirp_rate>-0.90022989063243</chirp_rate>
  <rfi_checked>0</rfi_checked>
  <rfi_found>0</rfi_found>
  <reserved>0</reserved>
</best_spike>
--- End code ---

as you see there are very small differencs in float numbers - different rounding ???

an other data are same

[attachment deleted by admin]

Gecko_R7:
Are the float/rounding differences enough to cause validation problem?

Radiohead:
<peak_power>22.561671618532</peak_power>
<peak_power>22.561794281006</peak_power>

<freq>1418974011.7011</freq>
<freq>1418975203.0489</freq>

<detection_freq>1418983759.2021</detection_freq>
<detection_freq>1418975184.9249</detection_freq>

Small???
 :) :) :)

Devaster:
yeah this is small to compare with  totally different previous results .... ;D
and yeah this problem by validation ....

Navigation

[0] Message Index

[#] Next page

[*] Previous page