DocumentCode :
2894684
Title :
A fully integrated multi-CPU, GPU and memory controller 32nm processor
Author :
Yuffe, Marcelo ; Knoll, Ernest ; Mehalel, Moty ; Shor, Joseph ; Kurts, Tsvika
Author_Institution :
Intel, Haifa, Israel
fYear :
2011
fDate :
20-24 Feb. 2011
Firstpage :
264
Lastpage :
266
Abstract :
This paper describes the 32nm Sandy Bridge processor that integrates up to 4 high performance Intel Architecture (IA) cores, a power/performance optimized graphic processing unit (GPU) and memory and PCIe controllers in the same die. The Sandy Bridge architecture block diagram is shown in Fig. 15.1.1 and the floorplan of a four IA-core version is shown in Fig. 15.1.2. The Sandy Bridge IA core implements an improved branch prediction algorithm, a micro-operation (Uop) cache, a floating point Advanced Vector Extension (AVX), a second load port in the L1 cache and bigger register files in the out-of-order part of the machine; all these architecture improvements boost the IA core performance without increasing the thermal power dissipation envelope or the average power consumption (to preserve battery life in mobile systems). The CPUs and GPU share the same 8MB level-3 cache memory. The data flow is optimized by a high performance on die interconnect fabric (called “ring”) that connects between the CPUs, the GPU, the L3 cache and the system agent (SA) unit that houses a 1600MT/s, dual channel DDR3 memory controller, a 20-lane PCIe gen2 controller, a two parallel pipe display engine, the power management control unit and the testability logic. An on die EPROM is used for configurability and yield optimization.
Keywords :
EPROM; cache storage; coprocessors; data flow analysis; electronic engineering computing; floating point arithmetic; logic testing; memory architecture; parallel architectures; peripheral interfaces; program compilers; AVX; EPROM; GPU processor; IA cores; PCIe controllers; PCIe gen2 controller; Sandy Bridge IA core; Sandy Bridge architecture block diagram; Uop cache; average power consumption; branch prediction algorithm; cache memory; configurability; data flow; die interconnect fabric; dual channel DDR3 memory controller; floating point advanced vector extension; high performance Intel architecture cores; memory controller processor; microoperation cache; multiCPU processor; optimized graphic processing unit; power management control unit; register files; sandy bridge processor; size 32 nm; system agent unit; testability logic; thermal power dissipation envelope; two parallel pipe display engine; yield optimization; Bridge circuits; Clocks; Graphics processing unit; Synchronization; Temperature sensors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Solid-State Circuits Conference Digest of Technical Papers (ISSCC), 2011 IEEE International
Conference_Location :
San Francisco, CA
ISSN :
0193-6530
Print_ISBN :
978-1-61284-303-2
Type :
conf
DOI :
10.1109/ISSCC.2011.5746311
Filename :
5746311
Link To Document :
بازگشت