* Yes, it is W*H*C*4.
* And my understanding is we can't directly access GPU memory so i copied all
my input data to CPU memory and then copied to GPU memory please excuse me if
my understanding was wrong.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/irrespective-of-input-same-outpu
Hello, I am studying tir and tir pass recently. And I found after I applying
pass `MakePackedAPI`, the function `tvm.build` will throw an error:
```
TVMError:
---
An error occurred during the execution of TVM.
For more information, ple
Hi all,
Just a generic question about debugging in GDB. Is there a good way to find the
proper type of an `"object"` in GDB?
What I mean by that is, say there is an `AddNode` passed to a function as a
`PrimExpr` and while debugging this function, is there way to find that it
actually belongs
[quote="myproject24, post:7, topic:10765"]
`w*h*c`
[/quote]
missing of `*4` - is it a problem of copy-past you forgot to compensate the
size of the float? since TVMArrayCopyFromBytes deal with bytes, not floats.
Another question why do you need m_gpuInput? you can use only NDArray been
alloca
how can i get the outputs info from mod?
we can get mode and params by calling from_onnx and from_caffe, as well as the
multiple outputs information corresponding to the mod. but if we call the
FoldConstant, the mod changes , how can i get the outputs info through the new
mod? is there a inte
When I build the onnx model, I performed the following optimizations:
with tvm.transform.PassContext(opt_level=3):
lib = relay.build_module.build(mod, target=target, params=params)
But after the program is executed to a certain position, there is no output
change in the termi
IIRC we made some immutability assumptions here that the passes won't modify
the original `IRModule`. We did find some bugs in the codebase previously the
module is incorrectly modified though :-(
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-efficiently-copy-an-ir/10798/5)
t
//data is float*
TVMArrayCopyFromBytes(m_cpuInput, data, w*h*c);
TVMArrayCopyFromTo(m_cpuInput, m_gpuInput, nullptr);
set_input("INPUT", m_gpuInput);
get_output(0, m_gpuOutput0);
TVMArrayCopyFromTo(m_gpuOutput0, m_cpuOutput0, nullptr);
---
[Visit
Topic](https://dis
[quote="myproject24, post:5, topic:10765"]
m_gpuInput is in metal context **kDLMetal**
[/quote]
How do you populate data to this NDArray?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/irrespective-of-input-same-output-ios-tvm-model/10765/6)
to respond.
You are receiving this because
This case seems to occur when we apply the basic block form pass. Other passes,
e.g., `FuseOps` will not result in such results. So I am wondering if it is
expected to modify the input argument (old module) by some passes.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-efficien
@junrushao1994 Thank you Junru! It did become faster!
Another related question is: will passes alter the original module (i mean if
`mod` will be modified after applying `new_mod = pass(mod)`). It seems this is
the case and I have to
m_gpuInput is in metal context **kDLMetal**
and I bundled JSON, Params, and dylib separately with the application I feel it
is more convenient to understand if any issue.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/irrespective-of-input-same-output-ios-tvm-model/10765/5)
to respon
I did not encounter this problem
What does your config.cmake file look like? especially the PAPI line?
Does PAPI work, if you run the tests or the binaries like `papi_native_avail`?
did you compile PAPI with `./configure --prefix=""
--with-components="cuda"`?
have you tried running `make cle
Hi, I came across the same problem as yours. I install the PAPI library in the
home directory, and the cmake result shows `Using PAPI library
pkgcfg_lib_PAPI_papi-NOTFOUND`. When I make the project, it also hints that the
papi.h file cannot be found. After adding the PAPI include directory, t
14 matches
Mail list logo
