MLBEDSW-2688: Improved LUT support
- Support for more than one 256-byte LUT in SHRAM
- No DMA is performed for a LUT that is already located in SHRAM
- Added MemArea.Shram, used for LUT, to avoid false address collision
asserts during SRAM tensor allocation
- Added read access to LUT in memory access calculation
Change-Id: If4d1eded5ed029d253f4f5efb2d80495fc3eac99
Signed-off-by: Louis Verhaard <louis.verhaard@arm.com>
diff --git a/ethosu/vela/numeric_util.py b/ethosu/vela/numeric_util.py
index 70209fb..4ebef8e 100644
--- a/ethosu/vela/numeric_util.py
+++ b/ethosu/vela/numeric_util.py
@@ -89,3 +89,7 @@
def full_shape(dim, shape, fill):
return ([fill] * (dim - len(shape))) + shape
+
+
+def overlaps(start1, end1, start2, end2):
+ return start1 < end2 and start2 < end1