diff options
| author | Eric Kunze <eric.kunze@arm.com> | 2021-09-28 16:15:42 -0700 |
|---|---|---|
| committer | Eric Kunze <eric.kunze@arm.com> | 2021-10-04 16:22:33 -0700 |
| commit | b6335b827cc58cd6776fe77907d5dfada6d4d93b (patch) | |
| tree | 642fb4bd351bda570499bd0749195e1f8521c8de /chapters/type_conversion.adoc | |
| parent | c949f8a3a554728ccb6ce0ee0992fde382160cda (diff) | |
| download | specification-b6335b827cc58cd6776fe77907d5dfada6d4d93b.tar.gz | |
Move quantization parameters into argument tables
The TOSA specification doesn't have quantized types.
Without those types, it is cleaner to move effects of quantization
such as the zero points into the standard list of arguments, rather
than existing as a separate table.
Change-Id: I18ea2959e9d3e4a3e9a0ead7a8ca319bb4426a47
Diffstat (limited to 'chapters/type_conversion.adoc')
| -rw-r--r-- | chapters/type_conversion.adoc | 11 |
1 files changed, 2 insertions, 9 deletions
diff --git a/chapters/type_conversion.adoc b/chapters/type_conversion.adoc index b947b73..8619fc3 100644 --- a/chapters/type_conversion.adoc +++ b/chapters/type_conversion.adoc @@ -82,15 +82,8 @@ Rescale quantized values into a new domain. This function scales by factor: mult |Input|in_t*|input|shape|Input tensor from 1 to 4 dims |Output|out_t*|output|shape|Output tensor with the same shape as input -|=== - -*Quantization Parameters:* - -|=== -|Argument|Type|Name|Shape|Description - -|Attribute|in_t|input_zp|-|Input tensor zero point -|Attribute|out_t|output_zp|-|Output tensor zero point +|Attribute|in_t|input_zp|-|Input tensor zero point. Must be zero for non-int8 types. +|Attribute|out_t|output_zp|-|Output tensor zero point. Must be zero for non-int8 types. |Input (MT profile) Attribute (BI/MI profiles)|mul_t|multiplier[NC]|-|Scaling multiplier array |Input (MT profile) Attribute (BI/MI profiles)|uint6_t|shift[NC] |-|Scaling shift array |Attribute|bool_t|scale32|-|if (scale32) mul_t=int32_t else mul_t=int16_t |