Directly below, I have copied the discussion of ARRAYS from the
Amibroker user manual.
Below this ARRAY explanation, is what AMD says about some
of their CPU processor's ability to process ARRAYS.
When AFL is evaluating statement like this ( High + Low )/2 it does not need
to re-interpret this code for each bar. Instead it takes the High ARRAY and Low
ARRAY and adds corresponding array elements in single stage. In other words +
operator (and other operators too) work on arrays at once and it is executed at
full compiled-code speed, then the resulting array (each element of it) is
divided by 2 also in single stage.
Let's look into the details - see fig 2.. When AFL engine looks at the ( High
+ Low )/2 it first takes High (1) and Low (2) arrays and produces (in single
compiled step) the temporary array (3). Then it creates the final array (4) by
dividing each element of temporary array by two. This result is assigned to
myVariable
|
Bar |
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
10 |
| 1 |
High (built-in array) |
1,24 |
1,27 |
1,25 |
1,29 |
1,25 |
1,29 |
1,35 |
1,35 |
1,37 |
1,29 |
| 2 |
Low (built-in array) |
1,20 |
1,21 |
1,19 |
1,20 |
1,21 |
1,24 |
1,30 |
1,28 |
1,31 |
1,27 |
| 3 |
High+Low (temporary array created during
evaluation) |
2,44 |
2,48 |
2,44 |
2,49 |
2,46 |
2,53 |
2,65 |
2,63 |
2,68 |
2,46 |
| 4 |
( High+Low ) /2 (gets assigned to MyVariable) |
1,22 |
1,24 |
1,22 |
1,245 |
1,23 |
1,265 |
1,325 |
1,315 |
1,34 |
1,23 |
Fig 2. AFL steps when processing ( High + Low ) /2
Below here is the AMD information.
====================================================
An
advanced HyperTransport link:
_•_This feature dramatically improves the I/O bandwidth,
enabling much faster access to peripherals such as hard drives, USB 2.0, and
Gigabit Ethernet cards.
_•_HyperTransport
technology enables higher performance due to a reduced I/O interface
throttle.
Large level one (L1)
and level 2 (L2) on-die cache:
_•_With 128 Kbytes of
L1 cache and 512K or 1MB of L2 cache per core, the AMD Athlon 64 and Athlon 64
X2 processors are able to excel at performing matrix calculations on
arrays.
_•_Programs that use intensive large matrix calculations will benefit
from fitting the entire matrix in the L2 cache.
=====================================================
Does anyone know if this AMD level-one and
level-two on-die cache will improve Amibroker's speed when it computes
hundreds of timeframes of RSI and hunderds of timeframes of STOCHK, all within
one custom indiocator window?? Rightnow, my 2001 Athlon1000 with 512 MB of
NONDDR Ram can plot two line sof this on the screen, but I have difficulty
moving the vertical line to the next EOD bar. TIA Ron D.
Please note that this group is for discussion between users only.
To get support from AmiBroker please send an e-mail directly to
SUPPORT {at} amibroker.com
For other support material please check also:
http://www.amibroker.com/support.html
YAHOO! GROUPS LINKS
|