diff options
| author | Kartik K. Agaram <vc@akkartik.com> | 2021-09-13 04:53:38 -0700 |
|---|---|---|
| committer | Kartik K. Agaram <vc@akkartik.com> | 2021-09-13 04:53:38 -0700 |
| commit | 77207192ea296f040c77cb41fd3966fecce813bb (patch) | |
| tree | 3e9ad343d9b054813eee3256a93dbfc9e509f0d8 /linux | |
| parent | 35c8c8edba84fd5c20f7cabd46d4824a88224f7b (diff) | |
| download | mu-77207192ea296f040c77cb41fd3966fecce813bb.tar.gz | |
.
Diffstat (limited to 'linux')
| -rw-r--r-- | linux/x86_approx.md | 8 |
1 files changed, 5 insertions, 3 deletions
diff --git a/linux/x86_approx.md b/linux/x86_approx.md index 059c5e6b..2835c08e 100644 --- a/linux/x86_approx.md +++ b/linux/x86_approx.md @@ -110,6 +110,8 @@ the fourth decimal place. Among the x86 instructions Mu supports, two are described in the Intel manual as "approximate": `reciprocal` (`rcpss`) and `inverse-square-root` (`rsqrtss`). Intel introduced these instructions as part of its SSE expansion in 1999. When -it upgraded SSE to SSE2 (in 2000), most of its single-precision floating-point -instructions got upgraded to double-precision — but not these two. So -they seem to be an evolutionary dead-end. +it upgraded SSE to SSE2 (in 2000), most of its scalar[1] single-precision +floating-point instructions got upgraded to double-precision — but not +these two. So they seem to be an evolutionary dead-end. + +[1] Thanks boulos for feedback: https://news.ycombinator.com/item?id=28501429#28507118 |