Itt az enyém:
Alap órajelen (200×10):

Procbench V0.61 Alpha, Peter Kuscsik, 2006-07-

Basic CPUID info:
~~~~~~~~~~~~~~~~~
Vendor    : AuthenticAMD
Family    : 15
Model    : 15
Revision  : 0
Name      : AMD Athlon(tm) 64 Processor 3200+
Features  : fpu vme de pse tsc msr pae mce cxchg8 apic sep mtrr pge mca cmov pat pse36 clfl mmx fxsr sse sse2

Data TLB (2 MB and 4 MB pages): Fully associative, 8 entries
Instruction TLB (2 MB and 4 MB pages): Fully associative, 8 entries
Data TLB (4 KB pages): Fully associative, 32 entries
Instruction TLB (4 KB pages): Fully associative, 32 entries
1st-level instr cache: 64 KBytes, 2-way set associative, 64 byte line size
1st-level data cache: 64 KBytes, 2-way set associative, 64 byte line size
2nd-level cache: 512 KBytes, 8-way set associative, 64 byte line size

Frequency [MHz]: 2014.997

Additional information
~~~~~~~~~~~~~~~~~~~~~~

Speed of registers measured by add instructions via 1, 2, 3 and 4 registers.
Speeds adding to      1 Register  2 Registers  3 Registers  4 Registers
16 bit Integer MIPS    2006        4026        5940        5882       
32 bit Integer MIPS    2006        4026        5940        5882       
32 bit MMX Integer MIPS 1006        2006        3015        4026       
64 bit FPU MFLOPS        502        1005        1511        2006       
32 bit 3DNow MFLOPS      503        1005        1507        2013       

Memory read performance test :
Read Buffer    Speed[MB/s]    Read Buffer    Speed[MB/s]
4 KBytes        28169        8 KBytes        28571
16 KBytes      28571        32 KBytes      28169
64 KBytes      27777        128 KBytes      9009
256 KBytes      9049          512 KBytes      5509
1 MByte        3710          2 MBytes        3717
4 MBytes        3683         

Generating:
1. Random numbers [200mills]:          0.497 seconds
2. Fibonicci numbers [200mills]:      0.298 seconds
3. Ackermann’s function [3,10]:        0.388 seconds
4. Cycle with Loop [500m times]:      0.746 seconds
5. Cycle with Jump [500m times]:      0.497 seconds
6. Primes (FPU based) [first 200k]:    0.731 seconds
7. Primes (Int based) [first 200k]:    1.003 seconds

Picit húzva (240×10):
Procbench V0.61 Alpha, Peter Kuscsik, 2006-07-

Basic CPUID info:
~~~~~~~~~~~~~~~~~
Vendor    : AuthenticAMD
Family    : 15
Model    : 15
Revision  : 0
Name      : AMD Athlon(tm) 64 Processor 3200+
Features  : fpu vme de pse tsc msr pae mce cxchg8 apic sep mtrr pge mca cmov pat pse36 clfl mmx fxsr sse sse2

Data TLB (2 MB and 4 MB pages): Fully associative, 8 entries
Instruction TLB (2 MB and 4 MB pages): Fully associative, 8 entries
Data TLB (4 KB pages): Fully associative, 32 entries
Instruction TLB (4 KB pages): Fully associative, 32 entries
1st-level instr cache: 64 KBytes, 2-way set associative, 64 byte line size
1st-level data cache: 64 KBytes, 2-way set associative, 64 byte line size
2nd-level cache: 512 KBytes, 8-way set associative, 64 byte line size

Frequency [MHz]: 2400.185

Additional information
~~~~~~~~~~~~~~~~~~~~~~

Speed of registers measured by add instructions via 1, 2, 3 and 4 registers.
Speeds adding to      1 Register  2 Registers  3 Registers  4 Registers
16 bit Integer MIPS    2400        4761        7058        7058       
32 bit Integer MIPS    2400        4800        7058        7058       
32 bit MMX Integer MIPS 1195        2400        3592        4800       
64 bit FPU MFLOPS        599        1197        1796        2400       
32 bit 3DNow MFLOPS      599        1197        1796        2400       

Memory read performance test :
Read Buffer    Speed[MB/s]    Read Buffer    Speed[MB/s]
4 KBytes        33898        8 KBytes        33898
16 KBytes      33898        32 KBytes      33333
64 KBytes      33898        128 KBytes      11428
256 KBytes      11428        512 KBytes      11173
1 MByte        4454          2 MBytes        4454
4 MBytes        4385         

Generating:
1. Random numbers [200mills]:          0.417 seconds
2. Fibonicci numbers [200mills]:      0.250 seconds
3. Ackermann’s function [3,10]:        0.326 seconds
4. Cycle with Loop [500m times]:      0.626 seconds
5. Cycle with Jump [500m times]:      0.417 seconds
6. Primes (FPU based) [first 200k]:    0.613 seconds
7. Primes (Int based) [first 200k]:    0.843 seconds

Én is csatlakozom.  🙂

Procbench V0.61 Alpha, Peter Kuscsik, 2006-07-

Basic CPUID info:
~~~~~~~~~~~~~~~~~
Vendor    : AuthenticAMD
Family    : 6
Model    : 10
Revision  : 0
Name      : AMD Athlon(tm) XP 3200+
Features  : fpu vme de pse tsc msr pae mce cxchg8 apic sep mtrr pge mca cmov pat pse36 mmx fxsr sse

Data TLB (2 MB and 4 MB pages):4-way set associative, 8 entries
Instruction TLB (2 MB and 4 MB pages): Fully associative, 8 entries
Data TLB (4 KB pages): Fully associative, 32 entries
Instruction TLB (4 KB pages): Fully associative, 16 entries
1st-level instr cache: 64 KBytes, 2-way set associative, 64 byte line size
1st-level data cache: 64 KBytes, 2-way set associative, 64 byte line size
2nd-level cache: 512 KBytes, 8-way set associative, 64 byte line size

Frequency [MHz]: 2297.822

Additional information
~~~~~~~~~~~~~~~~~~~~~~

Speed of registers measured by add instructions via 1, 2, 3 and 4 registers.
Speeds adding to      1 Register  2 Registers  3 Registers  4 Registers
16 bit Integer MIPS    1846        4000        4838        5263
32 bit Integer MIPS    1780        3821        4651        4800
32 bit MMX Integer MIPS  986        2097        2857        3750
64 bit FPU MFLOPS        491        1038        1550        2127
32 bit 3DNow MFLOPS      491        1039        1587        2105

Memory read performance test :
Read Buffer    Speed[MB/s]    Read Buffer    Speed[MB/s]
4 KBytes        18691        8 KBytes        25316
16 KBytes      18867        32 KBytes      27777
64 KBytes      16260        128 KBytes      5780
256 KBytes      5089          512 KBytes      2770
1 MByte        1512          2 MBytes        1569
4 MBytes        1552

Generating:
1. Random numbers [200mills]:          0.611 seconds
2. Fibonicci numbers [200mills]:      0.396 seconds
3. Ackermann’s function [3,10]:        0.452 seconds
4. Cycle with Loop [500m times]:      0.762 seconds
5. Cycle with Jump [500m times]:      0.529 seconds
6. Primes (FPU based) [first 200k]:    1.042 seconds
7. Primes (Int based) [first 200k]:    0.985 seconds

Enyje, mindenkinek ilyen menő gépje van? Na, azért, hogy ne csak atomerőművek legyenek:

Basic CPUID info:
~~~~~~~~~~~~~~~~~
Vendor    : GenuineIntel
Family    : 15
Model    : 2
Revision  : 7
Name      : Intel(R) Celeron(R) CPU 2.00GHz
Features  : fpu vme de pse tsc msr pae mce cxchg8 sep mtrr pge mca cmov pat pse36 clfl dtes acpi mmx fxsr sse sse2 ss htt tm1 cnxt-id

Instruction TLB: 4 KByte and 2-MByte or 4-MByte pages, 128 entries
Data TLB: 4 KByte and 4 MByte pages, 64 entries
1st-level data cache: 8 KByte, 4-way set associative, 64 byte line size
No 2nd-level cache or, if processor contains a valid 2nd-level cache, no 3rd-level cache
Trace cache: 12 K-µop, 8-way set associative

Frequency [MHz]: 1999.921

Additional information
~~~~~~~~~~~~~~~~~~~~~~
Official name : Mobile P4 Celeron 2,0
Codename : Northwood
Release : 01/2003
FSB : 100MHz
Datarate : QDR
Multiplier : 20.0x
VCore : 1.3V
Current : 33.3A
Power : 32.0W
Max temperature : 100.0øC
Transistors : 55.0M
Process : 130nm
Diesize : 131mm2

Speed of registers measured by add instructions via 1, 2, 3 and 4 registers.
Speeds adding to      1 Register  2 Registers  3 Registers  4 Registers
16 bit Integer MIPS    3508        4918        4958        4918       
32 bit Integer MIPS    3508        4958        4958        5042       
32 bit MMX Integer MIPS  881        1780        1734        1785       
64 bit FPU MFLOPS      —-        —-        —-        —-       
32 bit 3DNow MFLOPS    —-        —-        —-        —-       

Memory read performance test :
Read Buffer    Speed[MB/s]    Read Buffer    Speed[MB/s]
4 KBytes        12903        8 KBytes        12269
16 KBytes      6644          32 KBytes      6968
64 KBytes      6230          128 KBytes      1558
256 KBytes      1234          512 KBytes      1226
1 MByte        1233          2 MBytes        1241
4 MBytes        1254         

Generating:
1. Random numbers [200mills]:          0.779 seconds
2. Fibonicci numbers [200mills]:      0.291 seconds
3. Ackermann’s function [3,10]:        0.648 seconds
4. Cycle with Loop [500m times]:      0.595 seconds
5. Cycle with Jump [500m times]:      0.420 seconds
6. Primes (FPU based) [first 200k]:    2.741 seconds
7. Primes (Int based) [first 200k]:    1.196 seconds
32 bit Integer MIPS    3508        4958        4958        5042       
32 bit MMX Integer MIPS  881        1780        1734        1785       
64 bit FPU MFLOPS      —-        —-        —-        —-       
32 bit 3DNow MFLOPS    —-        —-        —-        —-       

Memory read performance test :
Read Buffer    Speed[MB/s]    Read Buffer    Speed[MB/s]
4 KBytes        12903        8 KBytes        12269
16 KBytes      6644          32 KBytes      6968
64 KBytes      6230          128 KBytes      1558
256 KBytes      1234          512 KBytes      1226
1 MByte        1233          2 MBytes        1241
4 MBytes        1254         

Generating:
1. Random numbers [200mills]:          0.779 seconds
2. Fibonicci numbers [200mills]:      0.291 seconds
3. Ackermann’s function [3,10]:        0.648 seconds
4. Cycle with Loop [500m times]:      0.595 seconds
5. Cycle with Jump [500m times]:      0.420 seconds
6. Primes (FPU based) [first 200k]:    2.741 seconds
7. Primes (Int based) [first 200k]:    1.196 seconds

Azért kíváncsi lennék, hogy ha lefordítanám, akkor mit produkálna 🙂

Ja, az hogy „egy gepi kodban irott”, kicsit nagyképű. Ezért nem is értettem először, hogy hogyan lehet akkor multiplatform. Azért asm!=gépi kod…

A 16 bit integer meg a 32 bit integer-ben a 3.2-es P4-em lenyomta az A64-eket?  ???  :tellme: WTF.
Jah, egyébként alapon mértem, majd fölrángatom 3.9 GHz-ig..  :wink1: