SAM 460 poor performance, high price

[dammy]

This thread has become yet another demonstration of this illustrative guide...

Guess by the end of the year, that chart will see v2.0 revision?  New players are coming in, they need to be included.

[kickstart]

Why people compare aros with morphos all time? mos and os4 at least are compatible with many classic applications just with a double click, this make a real amiga feeling (at least in morphos i never try os4).

[klx300r]

@ takemehomegrandma

 ..I think you need a calming visit to see grandma;)

boy I feel sorry for you & Piru when the X1000 arrives..better get your blood pressure medication ready:eek:

[runequester]

This thread has become yet another demonstration of this illustrative guide...

Would love to see that expanded to include classic amiga users

[Digiman]

Actually it would have been WindowsNT (yes serious).

OS-development under C= has allways been seriously underfunded and such were the results.

When C= bought Amiga most of the basics of the OS had allready been done and C= only made sure the biggest holes were filled in the cheapest/fastes way possible (the dreaded Tripos-DOS comes to mind).

1.1 was just a quickfix to allow for PAL-Amigas, 1.2 had some serious bugs removed, and 1.3 offered little beyond autobootsupport a basic Shell and support for more than 512k chipmen.

2.x was the 1st real update and that happened 5 years after C= bought Amiga.

Or in other words, if C= had started on the same basis as MorphOS did 10 years ago they wouldn't have gotten much further ...

1. Tripos under WB 1.x was superior to DOS/WIN 1 or 286/GEM MAC OS/RISC OS 1.

2. WIN NT was for when PA RISC for A5000 (A4000 successor) was a candidate CPU. Then they came to their senses and decided against it. NT was never going to replace Workbench on A1200 successors.

C= only needed to kill Medhi Ali and bury him under the foundations around 1991 to save their business though

[Digiman]

Would love to see that expanded to include classic amiga users

None of us want to spend £1500 in CPU/RAM/RTG cards for the pleasure of running them on £400 A4000s anyway though :roflmao:

[runequester]

None of us want to spend £1500 in CPU/RAM/RTG cards for the pleasure of running them on £400 A4000s anyway though :roflmao:

If it wont run on an 030 and AGA, it can bugger right off

[mike-]

http://papillon.is.tokushima-u.ac.jp/hardware/ppc460ex/ benchmark from the amcc 460ex eval board running at 800 mhz. There are some "real world" video decoding benchmark for the 440ep board, that can be compared to the 460ex eval board too. http://papillon.is.tokushima-u.ac.jp/hardware/ppc440ep/

460EX @ 800 mhz http://www.linuxfordevices.com/files/misc/amcc_canyonlands.jpg http://www.linuxfordevices.com/c/a/News/Embedded-PowerPC-dev-kits-come-with-Linux/
Dhrystone benchmark
-------------------

Dhrystone Benchmark, Version 2.1 (Language: C)

Program compiled with 'register' attribute

Please give the number of runs through the benchmark:
Execution starts, 333333333 runs through Dhrystone
Execution ends

Final values of the variables used in the benchmark:

Int_Glob: 5
should be: 5
Bool_Glob: 1
should be: 1
Ch_1_Glob: A
should be: A
Ch_2_Glob: B
should be: B
Arr_1_Glob[8]: 7
should be: 7
Arr_2_Glob[8][7]: 333333343
should be: Number_Of_Runs + 10
Ptr_Glob->
Ptr_Comp: 268521480
should be: (implementation-dependent)
Discr: 0
should be: 0
Enum_Comp: 2
should be: 2
Int_Comp: 17
should be: 17
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Next_Ptr_Glob->
Ptr_Comp: 268521480
should be: (implementation-dependent), same as above
Discr: 0
should be: 0
Enum_Comp: 1
should be: 1
Int_Comp: 18
should be: 18
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Int_1_Loc: 5
should be: 5
Int_2_Loc: 13
should be: 13
Int_3_Loc: 7
should be: 7
Enum_Loc: 1
should be: 1
Str_1_Loc: DHRYSTONE PROGRAM, 1'ST STRING
should be: DHRYSTONE PROGRAM, 1'ST STRING
Str_2_Loc: DHRYSTONE PROGRAM, 2'ND STRING
should be: DHRYSTONE PROGRAM, 2'ND STRING

User_Time = 119
Microseconds for one run through Dhrystone: 0.4
Dhrystones per Second: 2801120.5

=====================================================================
Whetstone benchmark results

Loops: 33333, Iterations: 1, Duration: 6 sec.
C Converted Double Precision Whetstones: 555.5 MIPS

=====================================================================

HINT Benchark
_ _
| | _ _ _ _____ TM
|-- | | |\ | | | |
| --| | | \ | |
| | | | \| |
^ ^ ^ ^ ^ ^

*** The HINT PERFORMANCE ANALYZER ***
Version 1.0 June 1994
John L. Gustafson & Quinn O. Snell
Scalable Computing Laboratory
236 Wilhelm, Iowa State University
Ames, Iowa 50011-3020
(515) 294 - 9294

Copyright (C) 1994 Iowa State University Research Foundation, Inc.
Please send results and questions to: hint@scl.ameslab.gov
When sending results please follow the form in README
________________________________________________________
RECT is 36 bytes
Apparent number of bits of accuracy: 31
Maximum associative whole number: 2147483647
Maximum number of bits of index: 30
Maximum representable index: 1073741824

Index-limited data accuracy: 31 bits
Maximum usable whole number: 2147483647
Grid: 32768 wide by 65536 high.
Precision is not sufficient for > 1.0 second runs.
.

=====================================================================
Stream benchmark results
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 2000000, Offset = 0
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 97490 microseconds.
(= 97490 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function Rate (MB/s) RMS time Min time Max time
Copy: 250.6307 0.1277 0.1277 0.1280
Scale: 237.9199 0.1345 0.1345 0.1346
Add: 254.4840 0.1886 0.1886 0.1887
Triad: 254.4489 0.1887 0.1886 0.1890

=====================================================================
MPEG-4 Encode results
---------------------
Input File: ./yuv/carphone%.3d, Frames encoded: 96, Total Time: 2.350000, Avg: enctime(ms) =24479.166667, fps =40.851064, length(bytes) = 416538
Input File: ./yuv/fg%.3d, Frames encoded: 21, Total Time: 1.760000, Avg: enctime(ms) =83809.523810, fps =11.931818, length(bytes) = 121033
MPEG-4 Decode results
---------------------
Input File: ./mp4u/carphone.mp4u, Frames decoded: 93, Total Time: 0.360000, Avg: decctime(ms) =3870.967742, fps =258.333333, length(bytes) = 4310
Input File: ./mp4u/fg.mp4u, Frames decoded: 21, Total Time: 0.200000, Avg: decctime(ms) =9523.809524, fps =105.000000, length(bytes) = 5763


440EP @ 533 mhz
=====================================================================
Dhrystone benchmark
-------------------

Dhrystone Benchmark, Version 2.1 (Language: C)

Program compiled with 'register' attribute

Please give the number of runs through the benchmark:
Execution starts, 333333333 runs through Dhrystone
Execution ends

Final values of the variables used in the benchmark:

Int_Glob: 5
should be: 5
Bool_Glob: 1
should be: 1
Ch_1_Glob: A
should be: A
Ch_2_Glob: B
should be: B
Arr_1_Glob[8]: 7
should be: 7
Arr_2_Glob[8][7]: 333333343
should be: Number_Of_Runs + 10
Ptr_Glob->
Ptr_Comp: 268521552
should be: (implementation-dependent)
Discr: 0
should be: 0
Enum_Comp: 2
should be: 2
Int_Comp: 17
should be: 17
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Next_Ptr_Glob->
Ptr_Comp: 268521552
should be: (implementation-dependent), same as above
Discr: 0
should be: 0
Enum_Comp: 1
should be: 1
Int_Comp: 18
should be: 18
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Int_1_Loc: 5
should be: 5
Int_2_Loc: 13
should be: 13
Int_3_Loc: 7
should be: 7
Enum_Loc: 1
should be: 1
Str_1_Loc: DHRYSTONE PROGRAM, 1'ST STRING
should be: DHRYSTONE PROGRAM, 1'ST STRING
Str_2_Loc: DHRYSTONE PROGRAM, 2'ND STRING
should be: DHRYSTONE PROGRAM, 2'ND STRING

User_Time = 177
Microseconds for one run through Dhrystone: 0.5
Dhrystones per Second: 1883239.2

=====================================================================
Whetstone benchmark results

Loops: 33333, Iterations: 1, Duration: 9 sec.
C Converted Double Precision Whetstones: 370.4 MIPS

=====================================================================
Stream benchmark results
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 2000000, Offset = 0
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 112424 microseconds.
(= 112424 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function Rate (MB/s) RMS time Min time Max time
Copy: 257.6116 0.1244 0.1242 0.1246
Scale: 253.1946 0.1265 0.1264 0.1267
Add: 254.3868 0.1888 0.1887 0.1889
Triad: 249.0738 0.1928 0.1927 0.1929

=====================================================================
MPEG-4 Encode results
Input File: ./yuv/carphone%.3d, Frames encoded: 96, Total Time: 4.160000, Avg: enctime(ms) =43333.333333, fps =23.076923, length(bytes) = 416538
Input File: ./yuv/fg%.3d, Frames encoded: 21, Total Time: 3.020000, Avg: enctime(ms) =143809.523810, fps =6.953642, length(bytes) = 121033

MPEG-4 Decode results
Input File: ./mp4u/carphone.mp4u, Frames decoded: 93, Total Time: 0.640000, Avg: decctime(ms) =6881.720430, fps =145.312500, length(bytes) = 4310
Input File: ./mp4u/fg.mp4u, Frames decoded: 21, Total Time: 0.300000, Avg: decctime(ms) =14285.714286, fps =70.000000, length(bytes) = 5763

Also worth noting from a different site: http://embedded-computing.com/amcc-powerpc-460ex-460gt-processors
Pricing and Availability

AMCCs 460EX and 460GT evaluation kits will be available in May and may be ordered from AMCC or any authorized distributor using part numbers EV-KIT-460EX-01 and EV-KIT-460GT-01. The suggested distributor resale price for each kit is $995. For more information, please contact your local AMCC sales office at http://www.amcc.com/Sales/.

AAND:
The old specs for the 460ex is to 1.2ghz, why this has changed i dont know, but if you look at that .jp site it does say 1.2.

Just for kicks im tracking down the benchmark used:
http://www.roylongbottom.org.uk/classic_benchmarks.tar.gz
http://www.cs.virginia.edu/stream/FTP/Code/
http://www.xvid.org/Downloads.43.0.html xvidcore/examples
http://trace.eas.asu.edu/yuv/carphone/carphone_qcif.7z ppffff!

Really? What are you basing this on?

The numbers I've seen are:

SAM460 AMCC460 1.167GHz

Code: [Select]

---> RAM <---
....

(source)

[Iggy]

@ takemehomegrandma

 ..I think you need a calming visit to see grandma;)

boy I feel sorry for you & Piru when the X1000 arrives..better get your blood pressure medication ready:eek:

Personally, I think when (if) the X1000 goes on sale, there will be 2.7 Ghz G5 Macs slapping its over priced butt silly.

[takemehomegrandma]

@ takemehomegrandma

 ..I think you need a calming visit to see grandma;)

boy I feel sorry for you & Piru when the X1000 arrives..better get your blood pressure medication ready:eek:

Don't worry. The x1000 won't have any real impact on the world whatsoever, except maybe as laughing stock in a similar way as if anyone would try to sell a stock 2007 specced Ford Focus at new Ferrari prices.

[takemehomegrandma]

Personally, I think when (if) the X1000 goes on sale, there will be 2.7 Ghz G5 Macs slapping its over priced butt silly.

Not entirely impossible you know...

[fishy_fiz]

The bottomline is I have actual hardware and software experience.  I am employed in a technical position.  I've been an IT admin and am currently a developer.  I did take courses in Computer Engineering.  People like you can understand simple concepts.

Fact: Quake3 will run faster on a SAM460 than on a G4 and that is directly because of video card performance.  Please return to your bridge.

Not sure if this has been mentioned yet, but the hardware interface is far from the be all end all of end results. Athlon64 in its day had much higher memory performance vs ddr2 when using only ddr1. Also, quality of drivers and support within an os can make a huge difference. Using Gallium3d (the eventually to be released gfx subsystem for OS4.x) itself is one example of proof of that. There's cases where a faster gpu is slower than a better supported weaker gpu, both with nvidia and ati/amd. Any benchamrks for mos vs. os4.x while mos is using a previous generation card on a pci interface vs. os4.x using agp on a card one generation newer? Going by the huge differences in performance for 3d between the 2, Id be surprised if there wasnt situations where mos (running same software) will outdo OS4.x, even when using a theoretically much weaker gfx card.

Now I actually say this as a fan of all "amiga" options, but I couldnt help refrain from commenting after your "I know better, Im smarter" tangen, which is followed up by inaccurate comments.

Now Ive also seen you comment about G5's being restricted to ddr2-533. One detail you seem to have omitted there is that it's capable of utilizing a dual channel memory controller.

[Fab]

Any benchamrks for mos vs. os4.x while mos is using a previous generation card on a pci interface vs. os4.x using agp on a card one generation newer? Going by the huge differences in performance for 3d between the 2, Id be surprised if there wasnt situations where mos (running same software) will outdo OS4.x, even when using a theoretically much weaker gfx card.

Well, on Quake3, even a MorphOS+Efika+radeon9250 combo beats a Pegasos/Aone/whatever+OS4+radeonwhatever combo. It tells quite a lot.

[Louis Dias]

Not sure if this has been mentioned yet, but the hardware interface is far from the be all end all of end results. Athlon64 in its day had much higher memory performance vs ddr2 when using only ddr1. Also, quality of drivers and support within an os can make a huge difference. Using Gallium3d (the eventually to be released gfx subsystem for OS4.x) itself is one example of proof of that. There's cases where a faster gpu is slower than a better supported weaker gpu, both with nvidia and ati/amd. Any benchamrks for mos vs. os4.x while mos is using a previous generation card on a pci interface vs. os4.x using agp on a card one generation newer? Going by the huge differences in performance for 3d between the 2, Id be surprised if there wasnt situations where mos (running same software) will outdo OS4.x, even when using a theoretically much weaker gfx card.

Here you include the software behind the hardware currently.  I was hoping to ignore the OS wars and was just looking at hardware (all else being equal) because nothing is stopping an MOS port except TeamMOS.

Now I actually say this as a fan of all "amiga" options, but I couldnt help refrain from commenting after your "I know better, Im smarter" tangen, which is followed up by inaccurate comments.

Now Ive also seen you comment about G5's being restricted to ddr2-533. One detail you seem to have omitted there is that it's capable of utilizing a dual channel memory controller.

None of this matters as the '460 won't support anything faster than DDR2-400 and it currently only running at DDR2-333 speeds.

[Colani1200]

Why people compare aros with morphos all time?

Why not?

mos and os4 at least are compatible with many classic applications just with a double click, this make a real amiga feeling (at least in morphos i never try os4).

The same thing is currently being developed for AROS. There are 2 different approaches atm (J-UAE and Emumiga).

[klx300r]

    Quote:
                                                                      Originally Posted by klx300r                                    
                 @ takemehomegrandma

 ..I think you need a calming visit to see grandma;)

boy I feel sorry for you & Piru when the X1000 arrives..better get your blood pressure medication ready:eek:
                                 
 Don't worry. The x1000 won't have any real impact on the world whatsoever, except maybe as laughing stock in a similar way as if anyone would try to sell a stock 2007 specced Ford Focus at new Ferrari prices.

hmm funny that when the X1000 was announced the major/ respected computer sources released positive reviews...heck one guy even ate his socks:) so who exactly will be laughing other than the same usual suspects here ?

I don't and won't worry because you won't see me running off to a MOS site bad mouthing anything new that's released for MOS but 'the usual suspects' make it an urgent matter to post trash on EVERY single new AmigaOS hardware or software release on Amiga sites....it's so obvious that it's laughable & sad really