IA-64 Vincent D. Capaccio.

Slides:



Advertisements
Similar presentations
Computer Organization and Architecture
Advertisements

Computer Architecture Instruction-Level Parallel Processors
® IA-64 Architecture Innovations John Crawford Architect & Intel Fellow Intel Corporation Jerry Huck Manager & Lead Architect Hewlett Packard Co.
Chapter 4 Predication CSE 820. Michigan State University Computer Science and Engineering Go over midterm exam.
CPE 731 Advanced Computer Architecture ILP: Part V – Multiple Issue Dr. Gheith Abandah Adapted from the slides of Prof. David Patterson, University of.
1 Advanced Computer Architecture Limits to ILP Lecture 3.
Chapter 4 CSF 2009 The processor: Instruction-Level Parallelism.
Prof. John Nestor ECE Department Lafayette College Easton, Pennsylvania ECE Computer Organization Lecture 19 - Pipelined.
Instruction Level Parallelism (ILP) Colin Stevens.
Chapter 15 IA-64 Architecture No HW, Concentrate on understanding these slides Next Monday we will talk about: Microprogramming of Computer Control units.
Prof. John Nestor ECE Department Lafayette College Easton, Pennsylvania Computer Organization Pipelined Processor Design 3.
Chapter 15 IA-64 Architecture. Reflection on Superscalar Machines Superscaler Machine: A Superscalar machine employs multiple independent pipelines to.
Chapter 21 IA-64 Architecture (Think Intel Itanium)
IA-64 Architecture (Think Intel Itanium) also known as (EPIC – Extremely Parallel Instruction Computing) a new kind of superscalar computer HW 5 - Due.
Chapter 15 IA-64 Architecture or (EPIC – Extremely Parallel Instruction Computing)
Computer Organization & Assembly Language
Semiconductor Memory 1970 Fairchild Size of a single core –i.e. 1 bit of magnetic core storage Holds 256 bits Non-destructive read Much faster than core.
Basic Microcomputer Design. Inside the CPU Registers – storage locations Control Unit (CU) – coordinates the sequencing of steps involved in executing.
The Pentium Processor Chapter 3 S. Dandamudi.
The Arrival of the 64bit CPUs - Itanium1 นายชนินท์วงษ์ใหญ่รหัส นายสุนัยสุขเอนกรหัส
Multiple Issue Processors: Superscalar and VLIW
Is Out-Of-Order Out Of Date ? IA-64’s parallel architecture will improve processor performance William S. Worley Jr., HP Labs Jerry Huck, IA-64 Architecture.
RISC By Ryan Aldana. Agenda Brief Overview of RISC and CISC Features of RISC Instruction Pipeline Register Windowing and renaming Data Conflicts Branch.
Spring 2003CSE P5481 VLIW Processors VLIW (“very long instruction word”) processors instructions are scheduled by the compiler a fixed number of operations.
RISC Architecture RISC vs CISC Sherwin Chan.
Introducing The IA-64 Architecture - Kalyan Gopavarapu - Kalyan Gopavarapu.
IA-64 Architecture RISC designed to cooperate with the compiler in order to achieve as much ILP as possible 128 GPRs, 128 FPRs 64 predicate registers of.
Chapter 8 CPU and Memory: Design, Implementation, and Enhancement The Architecture of Computer Hardware and Systems Software: An Information Technology.
Ted Pedersen – CS 3011 – Chapter 10 1 A brief history of computer architectures CISC – complex instruction set computing –Intel x86, VAX –Evolved from.
André Seznec Caps Team IRISA/INRIA 1 High Performance Microprocessors André Seznec IRISA/INRIA
Next Generation ISA Itanium / IA-64. Operating Environments IA-32 Protected Mode/Real Mode/Virtual Mode - if supported by the OS IA-64 Instruction Set.
Embedded Computer Architectures Hennessy & Patterson Chapter 4 Exploiting ILP with Software Approaches Gerard Smit (Zilverling 4102),
Use of Pipelining to Achieve CPI < 1
William Stallings Computer Organization and Architecture 6th Edition
CS 352H: Computer Systems Architecture
Computer Architecture
Computer Architecture Principles Dr. Mike Frank
William Stallings Computer Organization and Architecture 8th Edition
VLIW Architecture FK Boachie..
CPE 731 Advanced Computer Architecture ILP: Part V – Multiple Issue
Part IV Data Path and Control
COSC3330 Computer Architecture
X64.
Instruction-Level Parallelism
Chapter 14 Instruction Level Parallelism and Superscalar Processors
Flow Path Model of Superscalars
Part IV Data Path and Control
Instruction Level Parallelism and Superscalar Processors
The EPIC-VLIW Approach
BIC 10503: COMPUTER ARCHITECTURE
IA-64 Microarchitecture --- Itanium Processor
Yingmin Li Ting Yan Qi Zhao
Alex Saify Chad Reynolds James Aldorisio Brian Bischoff
Sampoorani, Sivakumar and Joshua
CC423: Advanced Computer Architecture ILP: Part V – Multiple Issue
Evolution of ISA’s ISA’s have changed over computer “generations”.
What is Computer Architecture?
What is Computer Architecture?
What is Computer Architecture?
Evolution of ISA’s ISA’s have changed over computer “generations”.
CSC3050 – Computer Architecture
DE NAYER INSTITUUT Hogeschool voor Wetenschap & Kunst
Evolution of ISA’s ISA’s have changed over computer “generations”.
CPU Structure CPU must:
Evolution of ISA’s ISA’s have changed over computer “generations”.
CSE378 Introduction to Machine Organization
Presentation transcript:

IA-64 Vincent D. Capaccio

IA-64 Overview Hewlett-Packard and Intel EPIC - Explicitly Parallel Instruction Computing 64-bit width Superscalar (Functional Units) Predication (Pre-computing branches) Speculation (Memory Hoisting) X86 is the ISA for Pentium… IA-64 is the ISA for the Itanium. Superscalar (parallel processing-functional units) Predication – Predicting the outcome of a conditional statement. Load both and get both answers. Then choose which path to take depending on the answer.

EPIC Explicitly Parallel Instruction Computing Smaller instruction set then RISC. Room on chip for more functional units and registers. Relies on Compiler to extract parallelism.

Functional Units (Superscalar) Computations completed in Parallel 6 Arithmetic Logic Units (ALU’s) 6 Specialized Multimedia Functional Units 1 Floating-Point Functional Units

Registers 128 64-bit General Purpose Registers r0-r31 are Static, r32-r127 are Dynamic 128 44-bit floating-Point Registers f0-f31 are Static, f32-f127 are Dynamic 64 1-bit Predicate Registers 8 Branch Registers At least 5 CUPID Registers

Predication (Pre-computing branches) With x86 ISA - 20%-30% process performance is wasted on guessing which branch to take. IA-64 takes BOTH paths (NO guessing) Predicate registers are used to know which answer to throw away.

Speculation (Memory Hoisting) Speculation is used to try to eliminate memory latency IA-64 looks ahead in code are loads data before it is needed.

Questions?