« Return to Thread: AMD Phenom: phenomenally slow
Re: AMD Phenom: phenomenally slow
by Mikhail Kuzminsky
::
Rate this Message:
In message from Clint Whaley <whaley@...> (Thu, 03 Jul 2008
10:16:08 -0500):
>Guys,
>
>I just got my hands on a Phenom X4. My understanding was this was
>the desktop
>version of the 3rd gen opteron (K10h). I expected it to have the
>same FPU
>peak: 4 flops/cycle double SSE, 8 flops/cycle single SSE, 2
>flops/cycle x87.
AMD says about "Wide FP Accelerator" for both Phenom X3/X4 and
Opteron.
For Opteron it's written directly - about 4 FLOP/cycle. For Phenom I
didn't find this data explicitly.
"Software Optimization Guide for AMD Family 10h Processors" says:
"Previous AMD64 processors supported 64-bit floating-point execution
units. The new AMD Family 10h processors add support for 128-bit
floating-point execution units. As a result, the throughput of both
single-precision and double-precision floating-point SSEx vector
operations has improved by 2X over the previous generation of AMD
processors."
Is Phenom a 10h Processor ? (May be 10h is a part of CPUID result ?).
>
>However, all my tests indicate it is 2/4/1 (I installed the Goto BLAS
>as well,
>and they also run at 1/2 speed compared to opteron). The Athlon-64
>was 2/4/2,
>so it appears to be much crappier than the previous generation
>hardware.
>Does anyone have any insight here? The AMD techdocs all lead me to
>believe
>4/8/x (no mention of x87, so crippling that is not as suprising).
>
>?
Atlas (make time) says me about 323.6% (max) on some dgemm on Opteron
2350/2 GHz, this corresponds to 6472 MFLOPS and can't be 2 DP FLOP per
cycle it's clear that chip has 8 GFLOPS.
Mikhail Kuzminsky,
Computer Assistance to Chemical Research Center
Zelinsky Institute of Organic Chemistry,
Moscow
>Clint
>
>**************************************************************************
>** R. Clint Whaley, PhD ** Assist Prof, UTSA **
>www.cs.utsa.edu/~whaley **
>**************************************************************************
>
>-------------------------------------------------------------------------
>Sponsored by: SourceForge.net Community Choice Awards: VOTE NOW!
>Studies have shown that voting for your favorite open source project,
>along with a healthy diet, reduces your potential for chronic
>lameness
>and boredom. Vote Now at http://www.sourceforge.net/community/cca08
>_______________________________________________
>Math-atlas-devel mailing list
>Math-atlas-devel@...
>https://lists.sourceforge.net/lists/listinfo/math-atlas-devel
-------------------------------------------------------------------------
Sponsored by: SourceForge.net Community Choice Awards: VOTE NOW!
Studies have shown that voting for your favorite open source project,
along with a healthy diet, reduces your potential for chronic lameness
and boredom. Vote Now at http://www.sourceforge.net/community/cca08
_______________________________________________
Math-atlas-devel mailing list
Math-atlas-devel@...
https://lists.sourceforge.net/lists/listinfo/math-atlas-devel
10:16:08 -0500):
>Guys,
>
>I just got my hands on a Phenom X4. My understanding was this was
>the desktop
>version of the 3rd gen opteron (K10h). I expected it to have the
>same FPU
>peak: 4 flops/cycle double SSE, 8 flops/cycle single SSE, 2
>flops/cycle x87.
AMD says about "Wide FP Accelerator" for both Phenom X3/X4 and
Opteron.
For Opteron it's written directly - about 4 FLOP/cycle. For Phenom I
didn't find this data explicitly.
"Software Optimization Guide for AMD Family 10h Processors" says:
"Previous AMD64 processors supported 64-bit floating-point execution
units. The new AMD Family 10h processors add support for 128-bit
floating-point execution units. As a result, the throughput of both
single-precision and double-precision floating-point SSEx vector
operations has improved by 2X over the previous generation of AMD
processors."
Is Phenom a 10h Processor ? (May be 10h is a part of CPUID result ?).
>
>However, all my tests indicate it is 2/4/1 (I installed the Goto BLAS
>as well,
>and they also run at 1/2 speed compared to opteron). The Athlon-64
>was 2/4/2,
>so it appears to be much crappier than the previous generation
>hardware.
>Does anyone have any insight here? The AMD techdocs all lead me to
>believe
>4/8/x (no mention of x87, so crippling that is not as suprising).
>
>?
Atlas (make time) says me about 323.6% (max) on some dgemm on Opteron
2350/2 GHz, this corresponds to 6472 MFLOPS and can't be 2 DP FLOP per
cycle it's clear that chip has 8 GFLOPS.
Mikhail Kuzminsky,
Computer Assistance to Chemical Research Center
Zelinsky Institute of Organic Chemistry,
Moscow
>Clint
>
>**************************************************************************
>** R. Clint Whaley, PhD ** Assist Prof, UTSA **
>www.cs.utsa.edu/~whaley **
>**************************************************************************
>
>-------------------------------------------------------------------------
>Sponsored by: SourceForge.net Community Choice Awards: VOTE NOW!
>Studies have shown that voting for your favorite open source project,
>along with a healthy diet, reduces your potential for chronic
>lameness
>and boredom. Vote Now at http://www.sourceforge.net/community/cca08
>_______________________________________________
>Math-atlas-devel mailing list
>Math-atlas-devel@...
>https://lists.sourceforge.net/lists/listinfo/math-atlas-devel
-------------------------------------------------------------------------
Sponsored by: SourceForge.net Community Choice Awards: VOTE NOW!
Studies have shown that voting for your favorite open source project,
along with a healthy diet, reduces your potential for chronic lameness
and boredom. Vote Now at http://www.sourceforge.net/community/cca08
_______________________________________________
Math-atlas-devel mailing list
Math-atlas-devel@...
https://lists.sourceforge.net/lists/listinfo/math-atlas-devel
« Return to Thread: AMD Phenom: phenomenally slow
| Free embeddable forum powered by Nabble | Forum Help |
