From 8939b5a2d69f25b1598d400133740f797eebd63f Mon Sep 17 00:00:00 2001 From: MITSUNARI Shigeo Date: Sun, 20 Oct 2024 05:44:07 +0900 Subject: [skip ci] [doc] tweak --- doc/usage.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/usage.md b/doc/usage.md index b28d772..5e1946a 100644 --- a/doc/usage.md +++ b/doc/usage.md @@ -161,7 +161,7 @@ feature|AVX-VNNI-INT8, AVX512-FP16|AVX10.2 1. `vmovd` and `vmovw` instructions with REG-to-XMM or XMM-to-REG operands are always encoded using AVX10.1. When used with XMM-to-XMM operands, these instructions are always encoded using AVX10.2. -2. `vmovd` and `vmovw` instructions with MEM-to-MEM operands support multiple encoding formats, including AVX, AVX512F, AVX512-FP16, and AVX10.2. +2. `vmovd` and `vmovw` instructions with XMM-to-MEM or MEM-to-XMM operands support multiple encoding formats, including AVX, AVX512F, AVX512-FP16, and AVX10.2. Initially, I tried implementing `setDefaultEncodingAVX10` using `EvexEncoding` (resp. `VexEncoding`) instead of `AVX10v2Encoding` (resp. `EvexEncoding`). However, I abandoned this approach after discovering the complexity of the encoding requirements of `vmovd` and `vmovw`. -- cgit v1.2.3