• Please review our updated Terms and Rules here

Looking for volunteers to help test a new benchmark

Chuck(G)

25k Member
Joined
Jan 11, 2007
Messages
39,711
Location
Pacific Northwest, USA
But the output you posted correctly shows 400Mhz...?

BTW, the CPU speed detection is based on known timings from known CPUs. If the code can't correctly detect the CPU, or has no timings for that CPU, the MHz speed is a best guess which will likely be wrong.

Yup, that 400MHz came from the non-debug test. I was surprised to see that DSTUB came up with a different value.
 

Compgeke

Veteran Member
Joined
Sep 30, 2011
Messages
780
Location
Fairfield, CA, USA
Here is a result from my newly built 486 DX2 system. Specs are 486 DX2 @ 66 MHz, 16 MB ram, I believe a Diamond Sleath 3D 2000 (S3 ViRGE), and a Tekram DC-390 SCSI controller.

[UID89D11154DF]
MemoryTest=82
OpcodeTest=45
VidramTest=179
MemEATest=54
3DGameTest=33
Score=170
CPU=Intel i486DX2
CPUspeed=66 MHz
BIOSinfo=(C)1985-1994,American Megatrends Inc.,All Rights Reserved,6145F Northbelt Parkway,GA-30071,USA.(404)-263-8181. (07/25/94, rev. 0)
MachineModel=01FC
BIOSdate=19940725
BIOSCRC16=89D1
VideoSystem=VGA
VideoAdapter=VGA, S3 86c868/86c968 PCI, VESA, 256kb Video Memory (BIOS)
Machine=AT clone

Here it is with Turbo disabled:
[UID89D1119644]
MemoryTest=262
OpcodeTest=168
VidramTest=491
MemEATest=235
3DGameTest=113
Score=55
CPU=Intel i486DX2
CPUspeed=66 MHz
BIOSinfo=(C)1985-1994,American Megatrends Inc.,All Rights Reserved,6145F Northbelt Parkway,GA-30071,USA.(404)-263-8181. (07/25/94, rev. 0)
MachineModel=01FC
BIOSdate=19940725
BIOSCRC16=89D1
VideoSystem=VGA
VideoAdapter=VGA, S3 86c868/86c968 PCI, VESA, 256kb Video Memory (BIOS)
Machine=AT clone

If I'm reading this correctly with Turbo disabled the performance drops significantly. Now to test with some different video cards :D.

Now, here is the Turbo result with a Hercules Stingray PCI card:
[UID89D111BE40]
MemoryTest=83
OpcodeTest=46
VidramTest=143
MemEATest=52
3DGameTest=33
Score=187
CPU=Intel i486DX2
CPUspeed=66 MHz
BIOSinfo=(C)1985-1994,American Megatrends Inc.,All Rights Reserved,6145F Northbelt Parkway,GA-30071,USA.(404)-263-8181. (07/25/94, rev. 0)
MachineModel=01FC
BIOSdate=19940725
BIOSCRC16=89D1
VideoSystem=VGA
VideoAdapter=VGA, VESA, 256kb Video Memory (BIOS)
Machine=AT clone

And Turbo disabled:
[UID89D111C239]
MemoryTest=243
OpcodeTest=170
VidramTest=460
MemEATest=236
3DGameTest=113
Score=58
CPU=Intel i486DX2
CPUspeed=66 MHz
BIOSinfo=(C)1985-1994,American Megatrends Inc.,All Rights Reserved,6145F Northbelt Parkway,GA-30071,USA.(404)-263-8181. (07/25/94, rev. 0)
MachineModel=01FC
BIOSdate=19940725
BIOSCRC16=89D1
VideoSystem=VGA
VideoAdapter=VGA, VESA, 256kb Video Memory (BIOS)
Machine=AT clone
.

Based on this here I believe the Hercules card is faster than the S3 card. The actual S3 chip is an Advance Logic chip, which was detected as a Standard VGA card. Now to test with some random no-name card.
 
Last edited:

Compgeke

Veteran Member
Joined
Sep 30, 2011
Messages
780
Location
Fairfield, CA, USA
Here is the same system, with a STB Systems video card with an S3 Virge GX chip.

Turbo:
[UID89D11203E2]
MemoryTest=82
OpcodeTest=45
VidramTest=139
MemEATest=53
3DGameTest=33
Score=185
CPU=Intel i486DX2
CPUspeed=66 MHz
BIOSinfo=(C)1985-1994,American Megatrends Inc.,All Rights Reserved,6145F Northbelt Parkway,GA-30071,USA.(404)-263-8181. (07/25/94, rev. 0)
MachineModel=01FC
BIOSdate=19940725
BIOSCRC16=89D1
VideoSystem=VGA
VideoAdapter=VGA, S3 86c868/86c968 PCI, VESA, 256kb Video Memory (BIOS)
Machine=AT clone

Turbo Disabled:
[UID89D1120782]
MemoryTest=247
OpcodeTest=170
VidramTest=438
MemEATest=236
3DGameTest=110
Score=56
CPU=Intel i486DX2
CPUspeed=66 MHz
BIOSinfo=(C)1985-1994,American Megatrends Inc.,All Rights Reserved,6145F Northbelt Parkway,GA-30071,USA.(404)-263-8181. (07/25/94, rev. 0)
MachineModel=01FC
BIOSdate=19940725
BIOSCRC16=89D1
VideoSystem=VGA
VideoAdapter=VGA, S3 86c868/86c968 PCI, VESA, 256kb Video Memory (BIOS)
Machine=AT clone
 

Chuck(G)

25k Member
Joined
Jan 11, 2007
Messages
39,711
Location
Pacific Northwest, USA
Another one--this is an FIC KC-19+ motherboard with a P3 Slot 1 533EB/133FSB CPU. It's a little unusual in that it's one of the Intel 820 boards using RDRAM. At any rate:
Code:
[UID1DDCE0C4]
MemoryTest=5
OpcodeTest=5
VidramTest=123
MemEATest=4
3DGameTest=2
Score=374
CPU=Intel Pentium III E
CPUspeed=500 MHz
BIOSinfo=unknown
MachineModel=01FC
BIOSdate=20000222
BIOSCRC16=1DDC
VideoSystem=VGA
VideoAdapter=VGA, ATI Bios : 0.0, VESA, 256kb Video Memory (BIOS)
Machine=AT clone

Two notes here: The BIOS is a Phoenix one and the CPU speed is 533MHz, not 500 (I can try it with other CPU speeds, if you'd like).
 

Cimonvg

Experienced Member
Joined
Apr 4, 2009
Messages
268
Location
scandinavia
hello
looked though the PRELIM.ZIP , but did not see 8088 10 Mhz. So one day soon ,I will test clone XT :)
/cimonvg
 

Todd82TA

Experienced Member
Joined
Jan 1, 2012
Messages
110
Location
Florida, USA
I've got...

I've got...

I've got an old Dell 325P which is a 386 DX-25. I bought it because it was considered (for the time) an ultra-small-form-factor computer. It's basically stock, 16mb of ram though at 70ns, and an on-board video card.

The only thing I did was install a Cyrix 486 DLC-40 to replace the 386 DX-25 chip. Would you like me to run a scan on my machine just for the heck of it?


Todd
 

njroadfan

Veteran Member
Joined
Jan 21, 2011
Messages
1,542
Sure, if anything to compare against a 386sx25 later. I have that same machine (nice small form factor, very nice box).

A friend of mine had a Dell 325p, it ran Windows 95 surprisingly well with 10MB of RAM. What was annoying is that it required parity SIMMs.
 

Todd82TA

Experienced Member
Joined
Jan 1, 2012
Messages
110
Location
Florida, USA
Ok, cool... I'll do it this weekend.

You know, before I could find the software online that would allow me to enable the chip cache... the processor would run REALLY slow. Using Norton System Info, it would actually run at exactly HALF the speed of a 386 DX-33.

With the cache enabled, it actually runs at a number which I believe would correspond to a 386 DX-40.


Strange, I would have thought that being a "486" would have made it a little bit quicker than a 386 DX-40.

The Seagate ST3144A (132mb hard drive) is also not as quick as I would like... but that sound is so nastoligc. I remember "back in the day" when my parents bought me an ST3144A for our Leading Edge D3/SX computer (386 SX-16), and man... was it expensive. It was like 500 bucks... but that was a HUGE drive back then.
 

Trixter

Veteran Member
Joined
Aug 31, 2006
Messages
7,259
Location
Chicagoland, Illinois, USA
While I have been tickled over the response to my little benchmark, I'm afraid I have to report that I won't be working on the code for a few weeks; I've injured my back somehow, and need to keep my sitting-in-a-chair time to a minimum. Please feel free to keep submitting machine profiles -- certainly the information itself is useful even without my full benchmark tool, especially since I posted the source code for each block in the PRELIM.ZIP file -- but I will likely be spending the next few weeks recuperating and learning new ergonomic habits to prevent this kind of injury again.

Sorry for the bummer post :-(
 

IBMMuseum

Veteran Member
Joined
Aug 28, 2006
Messages
1,449
While I have been tickled over the response to my little benchmark, I'm afraid I have to report that I won't be working on the code for a few weeks; I've injured my back somehow, and need to keep my sitting-in-a-chair time to a minimum. Please feel free to keep submitting machine profiles -- certainly the information itself is useful even without my full benchmark tool, especially since I posted the source code for each block in the PRELIM.ZIP file -- but I will likely be spending the next few weeks recuperating and learning new ergonomic habits to prevent this kind of injury again.

Sorry for the bummer post :-(

Get Well Soon...

Actually it is my intention this weekend to start getting baseline results on all of the stock standard IBM systems I can (i.e. Model 50 = x level, Model 50Z = x level, Model N51SX = x level, Model N51SLC = x level...)...
 

Trixter

Veteran Member
Joined
Aug 31, 2006
Messages
7,259
Location
Chicagoland, Illinois, USA
Cool, use the -d option to make sure the machine description is recorded as what the machine is exactly (my detection routines are neither comprehensive nor flawless).
 

IBMMuseum

Veteran Member
Joined
Aug 28, 2006
Messages
1,449
Cool, use the -d option to make sure the machine description is recorded as what the machine is exactly (my detection routines are neither comprehensive nor flawless).

I'm getting doubled-teamed by bad floppy diskettes and drives...

I've got a 50Z running (good config, with no battery errors), but had to go through drives for the best one...

And my Quad PPro (200MHz w/ 1Mb L1) I used to get the image apparently now has a flaky floppy, and is hell to switch (even temporarily)...

I shall persevere, resistance is futile...
 

Great Hierophant

Veteran Member
Joined
Mar 22, 2006
Messages
1,920
Location
Massachusetts, USA
While I have been tickled over the response to my little benchmark, I'm afraid I have to report that I won't be working on the code for a few weeks; I've injured my back somehow, and need to keep my sitting-in-a-chair time to a minimum. Please feel free to keep submitting machine profiles -- certainly the information itself is useful even without my full benchmark tool, especially since I posted the source code for each block in the PRELIM.ZIP file -- but I will likely be spending the next few weeks recuperating and learning new ergonomic habits to prevent this kind of injury again.

Sorry for the bummer post :-(

Get better soon, and if you could always install remote desktop software so that others could continue the good work!
 

IBMMuseum

Veteran Member
Joined
Aug 28, 2006
Messages
1,449
Cool, use the -d option to make sure the machine description is recorded as what the machine is exactly (my detection routines are neither comprehensive nor flawless).

Finally, success, but with some questions (this is a bone-stock 50Z, which is a zero wait-state system compared to the Model 50, and your program is being run from the hard drive):

Code:
[UID495EA5CEB]
MemoryTest=618
OpcodeTest=242
VidramTest=1242
MemEATest=295
3DGameTest=252
Score=19
CPU=Intel 80286
CPUspeed=10 MHz
BIOSinfo=        COPR. IBM 1981, 1987 (04/18/88, rev. 3)
MachineModel=04FC
BIOSdate=19880418
BIOSCRC16=495E
VideoSystem=VGA
VideoAdapter=VGA, unknown Chipset, 256kb Video Memory (BIOS)
Machine=PS/2 Model 50Z 286-10

...IBM PS/2 Model 50.

Code:
[UIDE8AEF3D81]
MemoryTest=746
OpcodeTest=318
VidramTest=1257
MemEATest=414
3DGameTest=312
Score=17
CPU=Intel 80286
CPUspeed=9.54 MHz
BIOSinfo=        COPR. IBM 1981, 1987 (02/13/87, rev. 0)
MachineModel=04FC
BIOSdate=19870213
BIOSCRC16=E8AE
VideoSystem=VGA
VideoAdapter=VGA, unknown Chipset, 256kb Video Memory (BIOS)
Machine=PS/2 Model 50 286-10
 

IBMMuseum

Veteran Member
Joined
Aug 28, 2006
Messages
1,449
Finally, success, but with some questions (this is a bone-stock 50Z, which is a zero wait-state system compared to the Model 50, and your program is being run from the hard drive):

Code:
[UID495EA5CEB]
MemoryTest=618
OpcodeTest=242
VidramTest=1242
MemEATest=295
3DGameTest=252
Score=19
CPU=Intel 80286
CPUspeed=10 MHz
BIOSinfo=        COPR. IBM 1981, 1987 (04/18/88, rev. 3)
MachineModel=04FC
BIOSdate=19880418
BIOSCRC16=495E
VideoSystem=VGA
VideoAdapter=VGA, unknown Chipset, 256kb Video Memory (BIOS)
Machine=PS/2 Model 50Z 286-10

A second stock 50Z (and good floppy drive), same BIOS revision, with only slight (except for the VRAM) changes:

(The first was an Intel 286-10, this is an AMD 286-10)

Code:
[UID495E26531]
MemoryTest=616
OpcodeTest=243
VidramTest=962
MemEATest=295
3DGameTest=252
Score=19
CPU=Intel 80286
CPUspeed=10 MHz
BIOSinfo=        COPR. IBM 1981, 1987 (04/18/88, rev. 3)
MachineModel=04FC
BIOSdate=19880418
BIOSCRC16=495E
VideoSystem=VGA
VideoAdapter=VGA, unknown Chipset, 256kb Video Memory (BIOS)
Machine=PS/2 Model 50Z 286-10
 

IBMMuseum

Veteran Member
Joined
Aug 28, 2006
Messages
1,449
A third 50Z (and good floppy drive), same BIOS revision, with IBM/Hyperace 486SLC2-50 CPU upgrade (switches are probably set to enable L1 and L2 cache), which crashes:

Code:
[UID495E168A1A]
MemoryTest=212
OpcodeTest=190
VidramTest=1270
MemEATest=229
3DGameTe
 
Last edited:

IBMMuseum

Veteran Member
Joined
Aug 28, 2006
Messages
1,449
And finally the IBM PC Convertible results:

Code:
[UID309D530]
MemoryTest=3573
OpcodeTest=1795
VidramTest=2010
MemEATest=1804
3DGameTest=1763
Score=4
CPU=Intel 8088 [no indication with current code that it is an 80C88]
CPUspeed=4.77 MHz
BIOSinfo=7396918 COPR. IBM 1985, 1987 (09/13/85, rev. 0)
MachineModel=00F9
BIOSdate=19850913
BIOSCRC16=3090
VideoSystem=CGA
VideoAdapter=CGA
Machine=PC Convertible
 

IBMMuseum

Veteran Member
Joined
Aug 28, 2006
Messages
1,449
50Z again, with an SX20LCMD (AMD 386SX-20 with Austek L2 cache module) Kingston "SX Now!" CPU upgrade:

(cache not enabled)

Code:
[UID495E2916]
MemoryTest=772
OpcodeTest=445
VidramTest=1292
MemEATest=534
3DGameTest=419
Score=14
CPU=Intel 386SX
CPUspeed=20 MHz
BIOSinfo=        COPR. IBM 1981, 1987 (04/18/88, rev. 3)
MachineModel=04FC
BIOSdate=19880418
BIOSCRC16=495E
VideoSystem=VGA
VideoAdapter=VGA, unknown Chipset, 256kb Video Memory (BIOS)
Machine=PS/2 Model 50Z 286-10


(cache enabled)

Code:
[UID495E854B]
MemoryTest=491
OpcodeTest=331
VidramTest=1281
MemEATest=428
3DGameTest=277
Score=25
CPU=Intel 386SX
CPUspeed=20 MHz
BIOSinfo=        COPR. IBM 1981, 1987 (04/18/88, rev. 3)
MachineModel=04FC
BIOSdate=19880418
BIOSCRC16=495E
VideoSystem=VGA
VideoAdapter=VGA, unknown Chipset, 256kb Video Memory (BIOS)
Machine=PS/2 Model 50Z 286-10
 
Top