AMD Opteron 4386 vs Intel Xeon E5-2643
Fizyczny
| Socket | AMD Socket C32 | Intel Socket 2011 |
|---|---|---|
| Rozmiar procesu | 32 nm | 32 nm |
| Tranzystory | 1,200 million | 1,270 million |
| Rozmiar matrycy | 315 mm² | 294 mm² |
| Pakiet | — | FC-LGA10 |
| Producent | — | Intel |
Wydajność
| Częstotliwość | 3.1 GHz | 3.3 GHz |
|---|---|---|
| Zegar turbo | up to 3.8 GHz | up to 3.5 GHz |
| Zegar bazowy | 200 MHz | 100 MHz |
| Mnożnik | 15.5x | 33.0x |
| Mnożnik odblokowany | No | No |
| TDP | 95 W | 130 W |
| Napięcie | — | 1.35 V |
Architektura
| Rynek | Server/Workstation | Server/Workstation |
|---|---|---|
| Status produkcji | unknown | unknown |
| Data wydania | Dec 4th, 2012 | Mar 6th, 2012 |
| Nazwa kodowa | Seoul | Sandy Bridge-EP |
| Generacja | Opteron | Xeon E5 |
| Część | OS4386WLU8KHK | SR0L7 |
| Obsługa pamięci | DDR3 | DDR3 Quad-channel |
| Pamięć ECC | No | Yes |
| PCI Express | — | Gen 3 |
Rdzenie
| Liczba rdzeni | 8 | 4 |
|---|---|---|
| Liczba wątków | 8 | 8 |
| SMP # CPUs | 2 | 2 |
| Zintegrowana karta graficzna | — | — |
Cache
| Cache L1 | 384K | 64K (per core) |
|---|---|---|
| Cache L2 | 8MB | 256K (per core) |
| Cache L3 | 8MB (shared) | 10MB (shared) |
Uwagi
| Uwagi | 16KB L1 data cache per core. 64KB L1 instruction cache shared per two cores (per module). 2MB L2 cache shared per two cores (per module). | — |
|---|
Cechy
| 8.0GT/s QPI | — | Yes |
|---|---|---|
| AES | Yes | — |
| AES-NI | — | Yes |
| AMD-V | Yes | — |
| AMD64 | Yes | — |
| AVX | Yes | Yes |
| CLMUL | Yes | — |
| CVT16 | Yes | — |
| EIST | — | Yes |
| EVP | Yes | — |
| FMA3 | Yes | — |
| FMA4 | Yes | — |
| HTT | — | Yes |
| Intel 64 | — | Yes |
| MMX | Yes | Yes |
| SSE | Yes | Yes |
| SSE2 | Yes | Yes |
| SSE3 | Yes | Yes |
| SSE4.1 | Yes | — |
| SSE4.2 | Yes | Yes |
| SSE4A | Yes | — |
| SSSE3 | Yes | Yes |
| TXT | — | Yes |
| VT-d | — | Yes |
| VT-x | — | Yes |
| XD bit | — | Yes |
| XOP | Yes | — |
