This document provides an overview of Intel's Core i7 processor, including details about its socket, instruction set, cores, and microarchitecture. It notes that the Core i7 was released in 2008 and uses Intel's QuickPath interconnect and Nehalem microarchitecture. It also describes the processor's clock speed, cache size, support for the SSE 4.2 instruction set, and Intel's Turbo Boost technology.
8. Core: Intel Quickpath Interconnect
• Intel X58 Arch
• Replaced front side bus
• Max width: 20 bit
• Max bandwidth: 16GB/s Unidirectional
• I7 920, 940
– 16 bit and 4.8 GT/s = 19.2 GB/s
• I7 965XE
– 16 bit and 6.4 GT/s = 25.6GB/s
9. Core: Nehalem
– 45nm architecture
– Scalable performance for from one-to-16 (or
more) threads and from one-to-eight (or
more) cores.
– Power usage
10. Core: EP & EX
• EP is for 2 sockets (the base layout)
• EX is for 4 and 8 sockets
– Is the EP duplicated with more interconnects
11.
12.
13. Core: 3 to 2 chip solution
• Named Westmere
• Moved GPU functionality from the
Northbridge onto the CPU
• Enables full disk encryption
Clock speed 2.66 GHz – 3.33GHz Cache 32 KB L1 instruction and 32 KB L1 data cache per core 256 KB L2 cache (combined instruction and data) per core 8 MB L3 (combined instruction and data) "inclusive", shared by all cores
Successor to the LGA 775 and completely incompatible I7 is the first to use the LGA 1366
x86, x86-64, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1 SSE4.2 CRC32 - Accumulate CRC32C value using the polynomial 0x11EDC6F41 (or, without the high order bit, 0x1EDC6F41) PCMPESTRI - Packed Compare Explicit Length Strings, Return Index PCMPESTRM - Packed Compare Explicit Length Strings, Return Mask PCMPISTRI - Packed Compare Implicit Length Strings, Return Index PCMPISTRM - Packed Compare Implicit Length String, Return Mask PCMPGTQ - Compare Packed Signed 64-bit data For Greater Than POPCNT - Population count (count number of bits set to 1) - bit manipulation; shares the same opcode for JMPE, the instruction used in Itanium CPUs to escape from IA-32 mode. POPCNT instruction may also be implemented in some processors that do not support the other SSE4 instructions and a separate bit can be tested to confirm POPCNT presence.
Power Usage Faster Synchronization Primitives Faster Handling of Branch Mispredictions Improved Hardware Prefetch and Better Load-Store Scheduling Improved Virtualization Performance. http://www.intel.com/technology/architecture-silicon/next-gen/whitepaper.pdf