1.1 Nehalem micro architecture
1.1.1 "Lynnfield" (45 nm)
1.1.2 "Bloomfield" (45 nm)
1.1.3 "Gulftown" (32 nm)
1.2 Sandy Bridge microarchitecture
1.2.1 "Sandy Bridge" (32 nm)
1.2.2 "Sandy Bridge-E" (32 nm)
1.2.3 "Ivy Bridge" (22 nm)
2 Mobile processors
2.1 Nehalem microarchitecture
2.1.1 "Clarksfield" (45 nm)
2.1.2 "Arrandale" (32 nm)
2.2 Sandy Bridge microarchitecture
2.2.1 "Sandy Bridge (Dual-Core)" (32 nm)
2.2.2 "Sandy Bridge (Quad-Core)" (32 nm)
2.2.3 "Ivy Bridge (Dual-Core)" (22 nm)
2.2.4 "Ivy Bridge (Quad-Core)" (22 nm)
Desktop
processors
"Lynnfield" (45 nm)
Lynnfield is the code name for a quad-core
processor from Intel
released in September 2009.[1]
It is sold in varying configurations as Core i5-7xx,
Core
i7-8xx or Xeon
X34xx. Lynnfield uses the Nehalem microarchitecture and replaces
the earlier Penryn based Yorkfield processor, using the same 45 nm process
technology, but a new memory and bus interface. The product code for Lynnfield
is 80605, its CPUID value identifies it as family 6, model 30 (0106Ex).
Lynnfield is
related to the earlier Bloomfield and Gainestown microprocessors, which are
used in server and high-end desktop systems. The main difference between the
two is Lynnfield's use of the LGA 1156 processor socket as opposed to the LGA 1366 used
in the others. LGA 1156 processors include Direct Media Interface and PCI Express
links, which Intel has previously connected to the processor with a dedicated northbridge chip, called the memory
controller hub or I/O hub.
The mobile
version of Lynnfield is Clarksfield.
Produced in 2009
Designed by Intel
Max. CPU clock rate 2.40 GHz
to 3.06 GHz
Min. feature size 45 nm
CPUID code 106Ex
Product code 80605
Cores 4
L2 cache 4x256kb
L3 cache 8 MB
Application Desktop
Socket(s) LGA 1156
- All models support: MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, Enhanced Intel SpeedStep Technology (EIST), Intel 64, XD bit (an NX bit implementation), TXT, Intel VT-x, Intel VT-d, Hyper-threading, Turbo Boost, Smart Cache.
- Core i7-875K features an unlocked multiplier and does not support Intel TXT and Intel VT-d.[1].
- FSB has been replaced with DMI.
- Transistors: 774 million
- Die size: 296 mm²
- Stepping: B1
"Bloomfield" (45 nm)
Bloomfield is the code name for Intel high-end
desktop processors sold as Core i7-9xx and single-processor servers sold as Xeon
35xx.,[1][2][3]
in almost identical configurations, replacing the earlier Yorkfield processors. The Bloomfield
core is closely related to the dual-processor Gainestown, which has the same CPUID
value of 0106Ax (family 6, model 26) and which uses the same socket. Bloomfield
uses a different socket than the later Lynnfield and Clarksfield processors based on the
same 45 nm Nehalem microarchitecture, even though
some of these share the same Intel
Core i7 brand.
Produced From 2008 to present
Designed by
Intel
Max. CPU clock rate
2.66 GHz to 3.33 GHz
CPUID code 106Ax
Product code 80601
Cores 4
L2 cache 4× 256 kB
L3 cache 8 MB
Application Desktop
Socket(s) LGA 1366
- All models support: MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, Enhanced Intel SpeedStep Technology (EIST), Intel 64, XD bit (an NX bit implementation), Intel VT-x, Hyper-threading, Turbo Boost, Smart Cache.
- FSB has been replaced with QPI.
- Transistors: 731 million
- Die size: 263 mm²
- Steppings: C0, D0
"Gulftown" (32 nm)
processor able to
run up to 12 threads in parallel. It is based on Westmere microarchitecture, the 32 nm
shrink of Nehalem.[3]
Originally rumored to be called the Intel Core i9, it is sold as an Intel
Core i7.[4]
The first release was the Core i7 980X in the first quarter of 2010,[5][6][7]
along with its server counterpart, the Xeon 3600 and the dual-socket Xeon 5600
(Westmere-EP) series using identical chips.
First figures
indicate that at equivalent clock rates, depending on the software, it has up
to 50% higher performance than the identically clocked quad core Bloomfield Core i7 975. However,
consumer software that utilizes six real cores is still quite rare as of 2011,
and not every multithreaded program is able to take advantage of this many
cores. Despite having 50% more transistors, the CPU strongly benefits from the
32-nm process, drawing the same or even less power (depending on the operating
system) than its Bloomfield predecessors with merely four cores. The thermal design power (TDP) of all planned
models is stated to be 130 watts.
Produced 1H 2010
Designed by Intel
Corporation
Max. CPU clock rate
3.2 GHz to 4.4 GHz
Min. feature size 32 nanometer
Instruction
set x86, x86-64, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AES-NI Microarchitecture
Westmere
CPUID code 0206Cx
Product code 80613, 80614
Cores
6 (physical), 12 (logical)
L2 cache 6 × 256 KB
L3 cache 12 MB
Application UP/DP Server, Workstation
Package(s) LGA-1366
Brand name(s) Core i7-970, 980, 980X,
990X, Xeon 3600s, 5600s
- All models support: MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, Enhanced Intel SpeedStep Technology (EIST), Intel 64, XD bit (an NX bit implementation), Intel VT-x, Hyper-threading, Turbo Boost, AES-NI, Smart Cache.
- Core i7-980X and -990X features an unlocked multiplier.
- FSB has been replaced with QPI.
- Transistors: 1170 million
- Die size: 239 mm²
- Steppings: B1
"Sandy
Bridge" (32 nm)
- All models support: MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, Enhanced Intel SpeedStep Technology (EIST), Intel 64, XD bit (an NX bit implementation), TXT, Intel VT-x, Intel VT-d, Hyper-threading, Turbo Boost, AES-NI, Smart Cache, Intel Insider (Digital rights management), vPro
- Support for up to 4 DIMMS of DDR3-1333 memory.
- S processors feature lower-than-normal TDP (65 W on 4-core models).
- K processors have unlocked turbo multiplier but does not support Intel TXT, Intel VT-d [2] and vPro.[3][4]
- Non-K processors will have limited turbo overclocking.
- Transistors: 1.16 billion[5]
- Die size: 216 mm²
"Sandy
Bridge-E" (32 nm)
- All models support: MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, Enhanced Intel SpeedStep Technology (EIST), Intel 64, XD bit (an NX bit implementation), Intel VT-x, Hyper-threading, Turbo Boost, AES-NI, Smart Cache.
- Support for up to 8 DIMMS of DDR3-1600 memory.
- Transistors: 1.27 (M1 stepping) or 2.27 (C1 stepping) billion
- Die size: 294 (M1 stepping) or 435 (C1 stepping) mm²
"Ivy Bridge" (22 nm)
- All models support: MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, Enhanced Intel SpeedStep Technology (EIST), Intel 64, XD bit (an NX bit implementation), TXT, Intel VT-x, Intel VT-d, Hyper-threading, Turbo Boost, AES-NI, Smart Cache, vPro
- Support for up to 4 DIMMS of DDR3-1600 memory.
- S processors feature lower-than-normal TDP (65 W on 4-core models).
- T processors feature an even lower TDP (45 W on 4-core models).
- K processors have unlocked turbo multiplier but does not support Intel TXT, Intel VT-d and vPro.
- Non-K processors will have limited turbo overclocking.
- Transistors: 1.4 billion
- Die size: 160 mm²
Mobile
processors
Clarksfield is the code name for an Intel
processor, initially sold as mobile Intel Core i7.[1] It is closely related to the desktop Lynnfield processor, both use quad-core dies
based on the 45 nm Nehalem
microarchitecture and
have integrated PCI Express and DMI links.
The predecessor
of Clarksfield, Penryn-QC was a multi-chip module with two dual-core Penryn dies based on
Penryn
microarchitecture, a
shrink of Core
microarchitecture. The
name of the direct successor of Clarksfield has not been announced. Arrandale is a later mobile processor but opens a
new line of mid-range dual-core processors with integrated graphics.
At the time of
its release at the Intel
Developer Forum on
September 23, 2009, Clarksfield processors were significantly faster than any
other laptop processor,[2]
including the Core 2 Extreme QX9300. The initial laptop manufacturers shipping
products based on Clarksfield processors include MSI, Dell/Alienware,
Hewlett-Packard, Toshiba and Asustek.[3]
Produced From
2009 to present
Min. feature size 45 nm
CPUID code 106Ex
Product code 80607
Cores 4
L2 cache
4x256kb
L3 cache 6
to 8 MB
Application Mobile
Socket(s) µPGA-988
- All models support: MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, Enhanced Intel SpeedStep Technology (EIST), Intel 64, XD bit (an NX bit implementation), TXT, Intel VT-x, Intel VT-d, Hyper-threading, Turbo Boost, Smart Cache.
- FSB has been replaced with DMI.
- Transistors: 774 million
- Die size: 296 mm²
- Steppings: B1
No comments:
Post a Comment