SCISM vs IA-64 Tagging: Differences/Code Density Effects
نویسندگان
چکیده
In this paper we first present two tagging mechanisms; the SCISM and IA-64; thereafter we describe the mapping of IA-64 ISA to a SCISM configuration without changing or reassigning the IA-64 instructions to preserve the original architectural properties. Under this limiting SCISM scenario, opcode reassignment will improve even more the SCISM performance, it is shown that SCISM tagging will significantly improve (between 21 and 29%) static code density. The results are based on analysis of various SPECINT2000 executables.
منابع مشابه
Ia-64 Code Generation Electrical and Computer Engineering Biographical Sketch
Rao, Vikram. IA-64 code generation. (Under the direction of Dr. Tom Conte). This work presents an approach to code generation for a new 64-bit Explicitly Parallel Instruction Computing (EPIC) architecture from Intel, called IA-64. The major contribution of this work is the design of a machine independent optimizer, munger, that transforms code generated originally for a Very Long Instruction Wo...
متن کاملIa-64 Code Generation Electrical and Computer Engineering Biographical Sketch 2 Prior Work 8 3 the Ia-64 Processor Architecture 17
Vikram Rao. IA-64 code generation. (Under the direction of Dr. Tom Conte). This work presents an approach to code generation for a new 64-bit Explicitly Parallel Instruction Computing (EPIC) architecture from Intel, called IA-64. The major contribution of this work is the design of a machine independent optimizer, munger, that transforms code generated originally for a Very Long Instruction Wor...
متن کاملSuperscalar Branch Instruction Processor
In this paper we describe the design of the branch unit that has been implemented in some models of the recently announced IBM AS/400 1. The branch unit we describe is a modification of the unit originally designed for the experimental IBM ESA/370 2 SCISM processor. The main feature of branch unit is its capability to remove branch instructions from the instruction stream dynamically and pre-pr...
متن کاملIA-64: A Parallel Instruction Set: 5/31/99
Finally allowing a full evaluation of their new instruction set, Intel and Hewlett-Packard have released a full description of IA-64’s application-level architecture and instruction set. The disclosures address some previous criticisms of the architecture and provide more details concerning how IA-64 processors will execute both x86 and PA-RISC binaries. The disclosures show a thoroughly modern...
متن کاملA Branch Instruction Processor for SCISM Organizations
The performance degradation caused by branch instructions in pipelined computers is well known. The degradation is even greater on computers with multiple pipelines processing a single instruction stream, such as superscalar and scalable compound instruction-set machines (SCISM). Several branch prediction schemes have been proposed that attempt to reduce this performance penalty. One of these {...
متن کامل