1997
DOI: 10.1145/384286.264126
|View full text |Cite
|
Sign up to set email alerts
|

Daisy

Abstract: Although VLIW architectures offer the advantages of simplicity of design and high issue rates, a major impedimegt to their use is that they are not compatible with the existing software base. We describe new simple hardware features for a VLIW machine we call DAISY (Dynamically Architected Instruction Set from Yorlrtown). DAISY is specifically intended to emulate existing architectures, so that all existing software for an old architecture (including operating system kernel code) runs without changes on the VL… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

1999
1999
2021
2021

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 38 publications
(4 citation statements)
references
References 14 publications
0
4
0
Order By: Relevance
“…However, to minimize the generated load/store instructions to access these architecture states, a BT usually maps such states to the physical registers on the target machine. In the past, many direct DBT systems (e.g., IA-32 Execution Layer [Baraz et al 2003], IBM's DAISY [Ebcioglu and Altman 1997], and HP's Aries [Zheng and Thompson 2000]) adopted one-to-one register mapping approaches where one source architecture register is mapped to a unique target register for the entire executable [Smith and Nair 2005], especially when the number of target architecture registers is more than the number of source architecture registers. However, this one-to-one mapping may not work for a retargetable DBT since the number of target registers may be fewer than the source registers.…”
Section: Register Mappingmentioning
confidence: 99%
See 3 more Smart Citations
“…However, to minimize the generated load/store instructions to access these architecture states, a BT usually maps such states to the physical registers on the target machine. In the past, many direct DBT systems (e.g., IA-32 Execution Layer [Baraz et al 2003], IBM's DAISY [Ebcioglu and Altman 1997], and HP's Aries [Zheng and Thompson 2000]) adopted one-to-one register mapping approaches where one source architecture register is mapped to a unique target register for the entire executable [Smith and Nair 2005], especially when the number of target architecture registers is more than the number of source architecture registers. However, this one-to-one mapping may not work for a retargetable DBT since the number of target registers may be fewer than the source registers.…”
Section: Register Mappingmentioning
confidence: 99%
“…Although there are many fast dynamic binary translators, they are usually machine specific [Baraz et al 2003;Ebcioglu and Altman 1997;Zheng and Thompson 2000]. QEMU [Bellard 2005] is a fast emulator that adopts retargetable DBT techniques.…”
Section: Dynamic Binary Translatorsmentioning
confidence: 99%
See 2 more Smart Citations