Hi, I'm using the ir_builder to contrust a cuda kernel, but I encounter a
problem of if_scope
```
ib = tvm.tir.ir_builder.create()
n = te.size_var("n")
A = ib.pointer("float32", name="A")
tmod = tvm.tir.truncmod
with ib.for_range(0, n, name="i") as i:
with ib.if_scope(tm
hi,I am new to TVM and I want to ask a q:
when using realy.build a lib and we can use time_evaluator to calculate the
time cost;
how to calculate the time when using create_executor?
I think
> start = time.time()
> tvm_output = intrp.evaluate()(tvm.nd.array(x.astype(dtype)),
**param
Hi everyone,
I'm currently trying to tensorize the schedule for a very simple [4,4] matrix
element-wise sum (add) to be performed in 4 [2,2] matrix addition steps by an
intrinsic function. I've looked into adapting the tutorial on
[Tensorization](https://tvm.apache.org/docs/tutorials/languag
[quote="cron, post:1, topic:9083"]
side of `te.extern` is blocking any kind of optimization which leads from
introducing this stage into an
[/quote]
Hi, I am also trying to apply some schedule primitive methods on
tensor.ExternOp, but it seems not supported according to this post (3 years'
ag
[quote="JosseVanDelm, post:1, topic:9335"]
```
Ab = tvm.tir.decl_buffer(a.shape, a.dtype, name="A", offset_factor=1,
strides=[2,1])
Bb = tvm.tir.decl_buffer(b.shape, b.dtype, name="B", offset_factor=1,
strides=[2,1])
Cb = tvm.tir.decl_buffer(c.shape, c.dtype, name="C", offset_factor
@leeexyz I can see it now too! This is really helpful! Thank you so much!
---
[Visit
Topic](https://discuss.tvm.apache.org/t/te-tensorize-elementwise-sum/9335/3) to
respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](http
Hi @SYangDong, use `b = tvm.tir.const(100, dtype="float32")` instead of the
assgiment directly.
---
[Visit Topic](https://discuss.tvm.apache.org/t/if-scope-in-ir-builder/9332/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [c
I'm not sure why MKLDNN_VERBOSE=1 doesn't work. The warning shows during the
compilation is fine. It just means that AutoTVM doesn't find a log record
corrsponding to "dense_mkldnn.x86".
---
[Visit
Topic](https://discuss.tvm.apache.org/t/mkldnn-verbose-doesnt-work/9315/4) to
respond.
Yo
Thank you @leeexyz. Yeah, we can use ```tvm.tir.const``` or a new buffer. I
means, it there any mechanism to prevent users using python variables within a
```if_scope```. For example, error message to tell users to utilize
```tvm.tir.const``` since it's quite easy to confuse the python varia
Oh
If i do not use autoTVM for tuning my graph, does mkldnn not be applied???
autoTVM : tuning my graph operation like 'for' loop (using tvm schedule
primitives), it is what i know..
then mkldnn or -libs options are used like tvm schedule primitives??
---
[Visit
Topic](https://discus
10 matches
Mail list logo