The 65-nm 16-MB Shared On-Die L3 Cache for the Dual-Core Intel Xeon Processor 7100 Series

The 16-way set associative, single-ported 16-MB cache for the Dual-Core Intel Xeon Processor 7100 Series uses a 0.624 mum² cell in a 65-nm 8-metal technology. Low power techniques are implemented in the L3 cache to minimize both leakage and dynamic power. Sleep transistors are used in the SRAM array and peripherals, reducing the cache leakage by more than 2X. Only 0.8% of the cache is powered up for a cache access. Dynamic cache line disable (Intel Cache Safe Technology) with a history buffer protects the cache from latent defects and infant mortality failures     

A 45 nm 8-Core Enterprise Xeon¯ Processor

This paper describes a 2.3 Billion transistors, 8-core, 16-thread, 64-bit Xeon^? EX processor with a 24 MB shared L3 cache implemented in a 45 nm nine-metal process. Multiple clock and voltage domains are used to reduce power consumption. Long channel devices and cache sleep mode are used to minimize leakage. Core and cache recovery improve manufacturing yields and enable multiple product flavors from the same silicon die. The disabled blocks are both clock and power gated to minimize their power consumption. Idle power is reduced by shutting off the unterminated I/O links and shedding phases in the voltage regulator to improve the power conversion efficiency.     

A Power-Efficient High-Throughput 32-Thread SPARC Processor

This first generation of "Niagara" SPARC processors implements a power-efficient Chip Multi-Threading (CMT) architecture which maximizes overall throughput performance for commercial workloads. The target performance is achieved by exploiting high bandwidth rather than high frequency, thereby reducing hardware complexity and power. The UltraSPARC T1 processor combines eight four-threaded 64-b cores, a floating-point unit, a high-bandwidth interconnect crossbar, a shared 3-MB L2 Cache, four DDR2 DRAM interfaces, and a system interface unit. Power and thermal monitoring techniques further enhance CMT performance benefits, increasing overall chip reliability. The 378-mm² die is fabricated in Texas Instrument's 90-nm CMOS technology with nine layers of copper interconnect. The chip contains 279 million transistors and consumes a maximum of 63 W at 1.2 GHz and 1.2 V. Key functional units employ special circuit techniques to provide the high bandwidth required by a CMT architecture while optimizing power and silicon area. These include a highly integrated integer register file, a high-bandwidth interconnect crossbar, the shared L2 cache, and the IO subsystem. Key aspects of the physical design methodology are also discussed     

A 130-nm triple-V/sub t/ 9-MB third-level on-die cache for the 1.7-GHz Itanium/spl reg/ 2 processor

The 18-way set-associative, single-ported 9 MB cache for the Itanium 2 processor uses 210 identical 48-kB sub-arrays with a 2.21-/spl mu/m/sup 2/ cell in a 130-nm 6-metal technology. The processor runs at 1.7 GHz at 1.35 V and dissipates 130 W. The 432-mm/sup 2/ die contains 592 M transistors, the largest transistor count reported for a microprocessor. This paper reviews circuit design and implementation details for the L3 cache data and tag arrays. The staged mode ECC scheme avoids a latency increase in the L3 tag. A high V/sub t/ implant improves the read stability and reduces the sub-threshold leakage.     

A 1.5-GHz 130-nm Itanium/sup /spl reg// 2 Processor with 6-MB on-die L3 cache

This 130-nm Itanium 2 processor implements the explicitly parallel instruction computing (EPIC) architecture and features an on-die 6-MB 24-way set-associative level-3 cache. The 374-mm/sup 2/ die contains 410 M transistors and is implemented in a dual-V/sub t/ process with six Cu interconnect layers and FSG dielectric. The processor runs at 1.5 GHz at 1.3 V and dissipates a maximum of 130 W. This paper reviews circuit design and package details, power delivery, the reliability, availability, and serviceability (RAS) features, design for test (DFT), and design for manufacturability (DFM) features, as well as an overview of the design and verification methodology. The fuse-based clock deskew circuit achieves 24-ps skew across the entire die, while the scan-based skew control further reduces it to 7 ps. The 128-bit front-side bus has a bandwidth of 6.4 GB/s and supports up to four processors on a single bus.     

A reconfigurable multilevel parallel texture cache memory with75-GB/s parallel cache replacement bandwidth

Recently, the level of realism in PC graphics applications has been approaching that of high-end graphics workstations, necessitating a more sophisticated texture data cache memory to overcome the finite bandwidth of the AGP or PCI bus. This paper proposes a multilevel parallel texture cache memory to reduce the required data bandwidth on the AGP or PCI bus and to accelerate the operations of parallel graphics pipelines in PC graphics cards. The proposed cache memory is fabricated by 0.16-μm DRAM-based SOC technology. It is composed of four components: an 8-MB DRAM L2 cache, 8-way parallel SRAM L1 caches, pipelined texture data filters, and a serial-to-parallel loader. For high-speed parallel L1 cache data replacement, the internal bus bandwidth has been maximized up to 75 GB/s with a newly proposed hidden double data transfer scheme. In addition, the cache memory has a reconfigurable architecture in its line size for optimal caching performance in various graphics applications from three-dimensional (3-D) games to high-quality 3-D movies     

A 4-MB on-chip L2 cache for a 90-nm 1.6-GHz 64-bit microprocessor

A 4-MB L2 data cache was implemented for a 64-bit 1.6-GHz SPARC(r) RISC microprocessor. Static sense amplifiers were used in the SRAM arrays and for global data repeaters, resulting in robust and flexible timing operation. Elimination of the global clock grid over the SRAM array saves power, enabled by combining the clock information with array select signals. Redundancy was implemented flexibly, with shift circuits outside the main data array for area efficiency. The chip integrates 315 million transistors and uses an 8-metal-layer 90-nm CMOS process.     

The implementation of the Itanium 2 microprocessor

This 64-b microprocessor is the second-generation design of the new Itanium architecture, termed explicitly parallel instruction computing (EPIC). The design seeks to extract maximum performance from EPIC by optimizing the memory system and execution resources for a combination of high bandwidth and low latency. This is achieved by tightly coupling microarchitecture choices to innovative circuit designs and the capabilities of the transistors and wires in the 0.18-/spl mu/m bulk Al metal process. The key features of this design are: a short eight-stage pipeline, 11 sustainable issue ports (six integer, four floating point, half-cycle access level-1 caches, 64-GB/s level-2 cache and 3-MB level-3 cache), all integrated on a 421 mm/sup 2/ die. The chip operates at over 1 GHz and is built on significant advances in CMOS circuits and methodologies. After providing an overview of the processor microarchitecture and design, this paper describes a few of these key enabling circuits and design techniques.     

A 65 nm 2-Billion Transistor Quad-Core Itanium Processor

This paper describes an Itanium processor implemented in 65 nm process with 8 layers of Cu interconnect. The 21.5 mm by 32.5 mm die has 2.05B transistors. The processor has four dual-threaded cores, 30 MB of cache, and a system interface that operates at 2.4 GHz at 105degC . High speed serial interconnects allow for peak processor-to-processor bandwidth of 96 GB/s and peak memory bandwidth of 34 GB/s.     

A 450-MHz RISC microprocessor with enhanced instruction set andcopper interconnect

This superscalar microprocessor is the first implementation of a 32-bit RISC architecture specification incorporating a single-instruction, multiple-data vector processing engine. Two instructions per cycle plus a branch can be dispatched to two of seven execution units in this microarchitecture designed for high execution performance, high memory bandwidth, and low power for desktop, embedded, and multiprocessing systems. The processor features an enhanced memory subsystem, 128-bit internal data buses for improved bandwidth, and 32-KB eight-way instruction/data caches. The integrated L2 tag and cache controller with a dedicated L2 bus interface supports L2 cache sizes of 512 KB, 1 MB, or 2 MB with two-way set associativity. At 450 MHz, and with a 2-MB L2 cache, this processor is estimated to have a floating-point and integer performance metric of 20 while dissipating only 7 W at 1.8 V. The 10.5 million transistor, 83-mm² die is fabricated in a 1.8-V, 0.20-μm CMOS process with six layers of copper interconnect     

The first IA-64 microprocessor

The first implementation of the IA-64 architecture achieves high performance by using a highly parallel execution core, while maintaining binary compatibility with the IA-32 instruction set. Explicitly parallel instruction computing (EPIC) design maximizes performance through hardware and software synergy. The processor contains 25.4 million transistors and operates at 800 MHz. The chip is fabricated in a 0.18-μm CMOS process with six metal layers and packaged in a 1012-pad organic land grid array using C4 (flip chip) assembly technology. A core speed back-side bus connects the processor to a 4-MB L3 cache     

A Sub-2 W Low Power IA Processor for Mobile Internet Devices in 45 nm High-k Metal Gate CMOS

This paper describes a low power Intel Architecture (IA) processor specifically designed for Mobile Internet Devices (MID) with performance similar to mainstream Ultra-Mobile PCs. The design relies on high residency in a new low-power state in order to keep average power and idle power below 220 and 80 mW, respectively. The design consists of an in-order pipeline capable of issuing 2 instructions per cycle supporting 2 threads, 32 KB instruction and 24 KB data L1 caches, independent integer and floating point execution units, times86 front end execution unit, a 512 KB L2 cache and a 533 MT/s dual-mode (GTL and CMOS) front-side-bus (FSB). The design contains 47 million transistors in a die size under 25 mm² manufactured in a 9-metal 45 nm CMOS process with optimized transistors for low leakage. Maximum thermal design power (TDP) consumption is measured at 2 W at 1.0 V, 90degC using a synthetic power-virus test at a frequency of 1.86 GHz.     

A dual-core 64-bit ultraSPARC microprocessor for dense server applications

A dual-core 64-bit microprocessor optimized for compute-dense systems such as rack-mount and blade servers for network computing was developed. The chip consists of two UltraSPARC II cores, each with its own 512 kB L2 cache, a DDR-1 memory controller, and symmetric multiprocessor bus (JBus) controllers. The 206-mm/sup 2/ die is fabricated in 0.13-/spl mu/m CMOS technology with seven layers of Cu and a low-k dielectric. The chip offers a highly efficient performance-per-watt ratio with a typical power dissipation of 23 W at 1.3 V and 1.2 GHz. A short design cycle was achieved by leveraging existing designs wherever possible and developing effective design methodologies and flows. Significant design challenges faced by this project are described. These include deep-submicron design issues, such as negative bias temperature instability (NBTI), leakage, coupling noise, intra-die process variation, and electromigration (EM). A second important design challenge was implementing a high-performance L2 cache subsystem with a short four-cycle core-to-L2 latency including ECC.     

Quantitative analysis and optimization techniques for on-chip cache leakage power

On-chip L1 and L2 caches represent a sizeable fraction of the total power consumption of microprocessors. In nanometer-scale technology, the subthreshold leakage power is becoming one of the dominant total power consumption components of those caches. In this study, we present optimization techniques to reduce the subthreshold leakage power of on-chip caches assuming that there are multiple threshold voltages, V/sub T/'s, available. First, we show a cache leakage optimization technique that examines the tradeoff between access time and subthreshold leakage power by assigning distinct V/sub T/'s to each of the four main cache components-address bus drivers, data bus drivers, decoders, and static random access memory (SRAM) cell arrays with sense amplifiers. Second, we show optimization techniques to reduce the leakage power of L1 and L2 on-chip caches without affecting the average memory access time. The key results are: 1) two additional high V/sub T/'s are enough to minimize leakage in a single cache-3 V/sub T/'s if we include a nominal low V/sub T/ for microprocessor core logic; 2) if L1 size is fixed, increasing L2 size can result in much lower leakage without reducing average memory access time; 3) if L2 size is fixed, reducing L1 size may result in lower leakage without loss of the average memory access time for the SPEC2K benchmarks; and 4) smaller L1 and larger L2 caches than are typical in today's processors result in significant leakage and dynamic power reduction without affecting the average memory access time.     

A 4.5-GHz 130-nm 32-KB L0 cache with a leakage-tolerant self reverse-bias bitline scheme

This paper describes a 32-KB two-read, one-write ported L0 cache for 4.5-GHz operation in 1.2-V 130-nm dual-V/sub TH/ CMOS technology. The local bitline uses a leakage-tolerant self reverse-bias (SRB) scheme with nMOS source-follower pullup access transistors, while preserving robust full-swing operation. Gate-source underdrive of -220 mV on the bitline read-select transistors is established without external bias voltages or gate-oxide overstress. Device-level measurements in the 130-nm technology show 72/spl times/ bitline active leakage reduction, enabling low-V/sub TH/ usage, 40% bitline keeper downsizing, and 16 bitcells/bitline. 11% faster read delay and 2/spl times/ higher dc noise robustness are achieved compared with high-performance dual-V/sub TH/ bitline scheme. Sustained performance and robustness benefits of the SRB technique against conventional dynamic bitline with scaling to 100- and 70-nm technology is also presented.     

Implementation of a fourth-generation 1.8-GHz dual-core SPARC V9 microprocessor

This fourth-generation processor combines two enhanced third-generation cores using an advanced 90-nm dual-Vt, dual-gate-oxide technology. Hardware additions feature expanded caches and inclusion of a 2-MB Level-2 cache and a Level-3 tag. Layout was completely redrawn to optimize the design for manufacturability and performance in the latest technology. Special emphasis was placed on library development to improve automation and assist in custom design. The memory design methodologies were completely updated to make quality design simpler and more robust. The chip operates at 1.8 GHz while dissipating 90 W of power at 1.1 V.     

A 125-mm/sup 2/ 1-Gb NAND flash memory with 10-MByte/s program speed

A single 3-V only, 1-Gb NAND flash memory has been successfully developed. The chip has been fabricated using 0.13-/spl mu/m CMOS STI technology. The effective cell size including the select transistors is 0.077 /spl mu/m/sup 2/. To decrease the chip size, a new architecture is introduced. The in-series connected memory cells are increased from 16 to 32. Furthermore, as many as 16 k memory cells are connected to the same wordline. As a result, the chip size is decreased by 15%. A very small die size of 125 mm/sup 2/ and an excellent cell area efficiency of 70% are achieved. As for the performance, a very fast programming and serial read are realized. The highest program throughput ever of 10.6-MByte/s is realized: 1) by quadrupling the page size and 2) by newly introducing a write cache. In addition, the garbage collection is accelerated to 9.4-MByte/s. In addition, the write cache accelerates the serial read operation and a very fast 20-MByte/s read throughput is realized.     

PMOS-Only Sleep Switch Dual-Threshold Voltage Domino Logic in Sub-65-nm CMOS Technologies

A circuit technique is proposed in this paper for simultaneously reducing the subthreshold and gate oxide leakage power consumption in domino logic circuits. Only p-channel sleep transistors and a dual-threshold voltage CMOS technology are utilized to place an idle domino logic circuit into a low leakage state. Sleep transistors are added to the dynamic nodes in order to reduce the subthreshold leakage current by strongly turning off all of the high-threshold voltage transistors. Similarly, the sleep switches added to the output nodes suppress the voltages across the gate insulating layers of the transistors in the fan-out gates, thereby minimizing the gate tunneling current. The proposed circuit technique lowers the total leakage power by up to 77% and 97% as compared to the standard dual-threshold voltage domino logic circuits at the high and low die temperatures, respectively. Similarly, a 22% to 44% reduction in the total leakage power is observed as compared to a previously published sleep switch scheme in a 45-nm CMOS technology. The energy overhead of the circuit technique is low, justifying the activation of the proposed sleep scheme by providing a net savings in total energy consumption during short idle periods.     

片上二级cache漏流功耗控制策略研究

 随着工艺尺寸缩小和处理器频率的提高,大容量的片上L2 cache成为处理器漏流功耗的主要来源.提出的保守多状态(C-SP&;SD)和推断多状态(S-SP&;SD)两种L2 cache漏流功耗控制策略能够将状态保留(State-Preserving)与状态破坏(State-Destroying)两种低功耗模式相结合.如果一个数据在多级cache存储层次中存在多个副本,那么只保留一个副本处于活跃状态,其他副本均被转换到低功耗模式,并且在不显著影响处理器性能的前提下尽可能转换到更低功耗的状态破坏模式.与传统的L2 cache漏流控制策略相比,C-SP&;SD策略以较小的处理器性能损失换取较大的L2 cache漏流功耗节省,而S-SP&;SD策略则实现了最优的L2 cache漏流功耗节省和处理器能量效率.     

A single-V/sub t/ low-leakage gated-ground cache for deep submicron

In this paper, we propose a novel integrated circuit and architectural level technique to reduce leakage power consumption in high-performance cache memories using single V/sub t/ (transistor threshold voltage) process. We utilize the concept of gated-ground (nMOS transistor inserted between ground line and SRAM cell) to achieve a reduction in leakage energy without significantly affecting performance. Experimental results on gated-ground caches show that data is retained (DRG-Cache) even if the memory is put in the standby mode of operation. Data is restored when the gated-ground transistor is turned on. Turning off the gated-ground transistor in turn gives a large reduction in leakage power. This technique requires no extra circuitry; the row decoder itself can be used to control the gated-ground transistor. The technique is applicable to data and instruction caches as well as different levels of cache hierarchy, such as the L1, L2, or L3 caches. We fabricated a test chip in TSMC 0.25-/spl mu/m technology to show the data retention capability and the cell stability of the DRG-Cache. Our simulation results on 100-nm and 70-nm processes (Berkeley Predictive Technology Model) show 16.5% and 27% reduction in consumed energy in L1 cache and 50% and 47% reduction in L2 cache, respectively, with less than 5% impact on execution time and within 4% increase in area overhead.