1)provide a better generic paddsub op implementation

2)make paddsub op support the Packet2cf/Packet4f/Packet2f in NEON
3)make paddsub op support the Packet2cf/Packet4f in SSE
This commit is contained in:
Guoqiang QI
2021-01-13 22:54:03 +00:00
committed by Rasmus Munk Larsen
parent 352f1422d3
commit 38ae5353ab
10 changed files with 115 additions and 40 deletions

View File

@@ -105,7 +105,8 @@
CHOLMOD_SUPPORTS_DOUBLE_PRECISION_ONLY=1,
SELFADJOINTVIEW_ACCEPTS_UPPER_AND_LOWER_MODE_ONLY=1,
INVALID_TEMPLATE_PARAMETER=1,
GPU_TENSOR_CONTRACTION_DOES_NOT_SUPPORT_OUTPUT_KERNELS=1
GPU_TENSOR_CONTRACTION_DOES_NOT_SUPPORT_OUTPUT_KERNELS=1,
THE_ARRAY_SIZE_SHOULD_EQUAL_WITH_PACKET_SIZE=1
};
};