MIPS R10000 Uses Decoupled Architecture: 10/24/94

نویسنده

  • Linley Gwennap
چکیده

Not to be left out in the move to the next generation of RISC, MIPS Technologies (MTI) unveiled the design of the R10000, also known as T5. As the spiritual successor to the R4000, the new design will be the basis of high-end MIPS processors for some time, at least until 1997. By swapping superpipelining for an aggressively out-oforder superscalar design, the R10000 has the potential to deliver high performance throughout that period. The new processor uses deep queues decouple the instruction fetch logic from the execution units. Instructions that are ready to execute can jump ahead of those waiting for operands, increasing the utilization of the execution units. This technique, known as out-of-order execution, has been used in PowerPC processors for some time (see 081402.PDF ), but the new MIPS design is the most aggressive implementation yet, allowing more instructions to be queued than any of its competitors. MIPS R10000 Uses De

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

The Mips R10000 superscalar microprocessor

cache refills early. he Mips RlOOOO is a dynamic, superscalar microprocessor that implements T the 64-bit Mips 4 instruction set architecture. It fetches and decodes four instructions per cycle and dynamically issues them to five fully-pipelined, low-latency execution units. Instructions can be fetched and executed speculatively beyond branches. Instructions graduate in order upon completion. A...

متن کامل

PA-8000 Combines Complexity and Speed: 11/14/94

Long a proponent of simple, fast processors, HP has succumbed to the siren call of complexity, creating the most feature-filled RISC design yet revealed. Steve Manglesdorf, presenting at last month’s Microprocessor Forum, said that the forthcoming PA-8000 will achieve high clock rates despite the burden of this feature set, a powerful combination that he claims will create the industry’s fastes...

متن کامل

The nMips R10000 Superscalar Microprocessor - IEEE Micro

cache refills early. he Mips RlOOOO is a dynamic, superscalar microprocessor that implements T the 64-bit Mips 4 instruction set architecture. It fetches and decodes four instructions per cycle and dynamically issues them to five fully-pipelined, low-latency execution units. Instructions can be fetched and executed speculatively beyond branches. Instructions graduate in order upon completion. A...

متن کامل

A Study of Out-of-Order Completion for the MIPS R10K Superscalar Processor

Instruction level parallelism (ILP) improves performance for VLIW, EPIC, and Superscalar processors. Out-of-order execution improves performance further. The advantage of out-of-order execution is not fully utilized due to in-order completion. In this report we study the performance loss due to in-order completion for MIPS R10000 processor.

متن کامل

Performance Analysis Using SvPablo

In this tutorial we present SvPablo, a graphical source code browser and performance visualizer that integrates the University of Illinois Pablo project's dynamic performance instrumentation software with HPF and C compilers and with the MIPS R10000 hardware performance mechanism. The following topics will be covered in the tutorial: an introduction to the SvPablo environment, including an over...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1994