From 2867c85a3754320f96e36afb63325bb76269caa4 Mon Sep 17 00:00:00 2001
From: Duncan Sands fpmath metadata may be attached to any instruction of floating point
type. It can be used to express the maximum acceptable error in the result of
that instruction, in ULPs, thus potentially allowing the compiler to use a
- more efficient but less accurate method of computing it. The number of ULPs
- may also be the string "fast", which tells the compiler that speed
- matters more than accuracy, so any fairly accurate method of computation is
- fine as long as it is quick. ULP is defined as follows:
@@ -3024,13 +3022,11 @@ call void @llvm.dbg.value(metadata !24, i64 0, metadata !25)
The metadata node shall consist of a single positive floating point number - representing the maximum relative error, or the string "fast". - For example:
+ representing the maximum relative error, for example:!0 = metadata !{ float 2.5 } ; maximum acceptable inaccuracy is 2.5 ULPs -!1 = metadata !{ !metadata !"fast" } ; potentially unbounded inaccuracy