tkonolige commented on a change in pull request #10839:
URL: https://github.com/apache/tvm/pull/10839#discussion_r839875335
##########
File path: python/tvm/topi/arm_cpu/tensor_intrin.py
##########
@@ -614,21 +614,22 @@ def _instr(index):
ib.emit(outs[0].vstore(0, tvm.tir.const(0, int_32xl)))
return ib.get()
- def pairwise_add_mul(idx):
- # this broadcasts data to the vector size
- a_int8 = ins[0].vload([0], "int8x4")
- re_int32 = tvm.tir.call_intrin("int32", "tir.reinterpret",
a_int8)
- vec_ai32 = re_int32.astype("int32x2")
- vec_a = tvm.tir.call_intrin(int_8xl, "tir.reinterpret",
vec_ai32)
+ # this broadcasts data to the vector size
+ a_int8 = ins[0].vload([0], "int8x4")
+ re_int32 = tvm.tir.call_intrin("int32", "tir.reinterpret", a_int8)
+ vec_ai32 = re_int32.astype("int32x2")
+ vec_a = tvm.tir.call_intrin(int_8xl, "tir.reinterpret", vec_ai32)
- vec_b = ins[1].vload([idx * 2, 0], int_8xl) # we take two
inputs at a time
+ vec_b = ins[1].vload([0, 0], "int8x16")
+ def pairwise_add_mul(extract_half):
+ vec_b_half = tvm.tir.call_intrin("int8x8", extract_half, vec_b)
Review comment:
This seems fine.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
