[PATCH v4 2/7] x86: decode EVEX 0F38 4B by length
Project / Subsystem
binutils / x86
Date
2026-09-29
Proposer
Rohan Shenoy <RohanRadhesh.Shenoy@amd.com>
Source type
public_inbox
Consensus
Proposed
Sentiment
—/10
Technical tradeoffs
- • Improves decoder accuracy for a specific instruction encoding.
- • Enables support for future instruction sets like ACE.
All attributes
- project
- binutils
- subsystem
- x86
- patch_id
- —
- discussion_id
- 0ed0b87d09a08fe6f3093838df68d04491c42ce4.1790705096.git.RohanRadhesh.Shenoy@amd.com
- source_type
- public_inbox
- title
- [PATCH v4 2/7] x86: decode EVEX 0F38 4B by length
- headline
- x86: decode EVEX 0F38 4B by length
- tldr
- Modifies the EVEX decoder to correctly handle instructions with non-zero L'L, a prerequisite for ACE instructions.
- proposer
- Rohan Shenoy <RohanRadhesh.Shenoy@amd.com>
- consensus
- Proposed
- outcome
- proposed
- sentiment_score
- —
- technical_tradeoffs
-
- • Improves decoder accuracy for a specific instruction encoding.
- • Enables support for future instruction sets like ACE.
- series_id
- binutils:x86: decode evex 0f38 4b by length
- series_role
- reply
- series_parts
- []
- tags
-
- • x86
- • EVEX
- • decoder
- • ACE
- bugzilla_url
- —
- date
- 2026-09-29T00:00:00.000Z
[PATCH v4 2/7] x86: decode EVEX 0F38 4B by length
This patch adjusts the EVEX decoder in binutils to properly process entries where the L’L field is non-zero. This is a necessary change to ensure that ACE instructions, which may utilize non-zero L’L values, are decoded correctly.