diff options
| author | Dominic Symes <dominic.symes@arm.com> | 2021-05-26 17:44:19 +0100 |
|---|---|---|
| committer | Dominic Symes <dominic.symes@arm.com> | 2021-05-26 17:44:46 +0100 |
| commit | 7a2e08cdb14fd198a6f15468e24dd98791990df8 (patch) | |
| tree | 51eb418cf95863644a85e7f12fd1e09aa1bfea71 | |
| parent | ed1b5a96e133045222f3240c979f6aef40dc43f7 (diff) | |
| download | specification-7a2e08cdb14fd198a6f15468e24dd98791990df8.tar.gz | |
Rename and clarify the divide operator.
Name changed from DIV to INTDIV.
Usage clarified.
Change-Id: I493b8ace7a63e4c80caac1674c767c1ad468dd83
Signed-off-by: Dominic Symes <dominic.symes@arm.com>
| -rw-r--r-- | chapters/ewise_binary.adoc | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/chapters/ewise_binary.adoc b/chapters/ewise_binary.adoc index 18518bd..45075e9 100644 --- a/chapters/ewise_binary.adoc +++ b/chapters/ewise_binary.adoc @@ -208,12 +208,13 @@ for_each(index in shape) { |Any|signed 32|int32_t |=== -==== DIV +==== INTDIV -Elementwise divide of input1 by input2. +Elementwise integer divide of input1 by input2. The result of the divide is truncated towards zero. -Only used for integer operation. +Expected use is for operations on non-scaled integers. Floating point divide should use RECIPROCAL and MUL. +Quantized integer divide should use TABLE (for 1/x) and MUL. *Arguments:* |