# Type casting a buffer

**URL:** <https://discuss.tvm.apache.org/t/type-casting-a-buffer/4035>\
**Category:** Development\
**Created:** [September 17, 2019, 6:45pm UTC](https://discuss.tvm.apache.org/t/type-casting-a-buffer/4035 "2019-09-17T18:45:32Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![kparzysz](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/kparzysz/32/252_2.png) [@kparzysz](https://discuss.tvm.apache.org/u/kparzysz)\
**Post date:** [September 17, 2019, 6:45pm UTC](https://discuss.tvm.apache.org/t/type-casting-a-buffer/4035/1 "2019-09-17T18:45:32Z")

</div>

If I have a buffer of type `int8`, and I want to treat it as a buffer of `int32`, what is the best way to do it? Right now, I do

```auto
x32 = tvm.decl_buffer(x8.shape, 'int32', 'name', x8.data,
                      x8.strides, x8.elem_offset, x8.scope,
                      x8.data_alignment, x8.offset_factor)

```

i.e. create a new buffer with the same parameters as before, but with a different type. This is just for prototyping (the shapes are incorrect, etc.), but I was wondering if there is a better way of doing it.

What I really want is to do `x8.vload(0, 'int32x32')`, i.e. a load of a vector of `i32` from a buffer of type `int8`.

---

<div class="post-metadata">

**Author:** ![tqchen](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/tqchen/32/5_2.png) [@tqchen](https://discuss.tvm.apache.org/u/tqchen)\
**Post date:** [September 17, 2019, 7:01pm UTC](https://discuss.tvm.apache.org/t/type-casting-a-buffer/4035/2 "2019-09-17T19:01:17Z")

</div>

creating a buffer view is one way to do it.

On the other hand, making most buffers have a single element type will compiler’s life easy. Can you elaborate why do we want the alias int8 buffer as in32 instead of directly declaring it as int32?

---

<div class="post-metadata">

**Author:** ![kparzysz](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/kparzysz/32/252_2.png) [@kparzysz](https://discuss.tvm.apache.org/u/kparzysz)\
**Post date:** [September 17, 2019, 7:15pm UTC](https://discuss.tvm.apache.org/t/type-casting-a-buffer/4035/3 "2019-09-17T19:15:38Z")

</div>

I’m trying to generate LLVM intrinsics for HVX instructions. A vector register doesn’t have a type, so in assembly it’s possible to do

```auto
  v0 = vadd(v0.b, v1.b) // treat v0 as vector of bytes
  v1 = vsub(v0.w, v2.w) // treat v0 as vector of words

```

Originally HVX was programmed using C intrinsics, and for each of these, there is an LLVM intrinsic. To allow the above assembly in C, all C and LLVM intrinsics are declared as working on vectors of `int32` (regardless of what type they actually operate on).

As a consequence, if we have a buffer of `int8` and we want to invoke an LLVM vector intrinsic for HVX, we have to use type `int32x32`.

---

<div class="post-metadata">

**Author:** ![FrozenGene](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/frozengene/32/1114_2.png) [@FrozenGene](https://discuss.tvm.apache.org/u/FrozenGene)\
**Post date:** [September 18, 2019, 2:24am UTC](https://discuss.tvm.apache.org/t/type-casting-a-buffer/4035/4 "2019-09-18T02:24:22Z")

</div>

Maybe one bit stray from the point, I think we could implement it in CodeGen. Like this:

```auto
  // LLVM's HVX vector intrinsics don't include the type of the
  // operands, they all operate on vectors of 32 bit integers.
  for (size_t i = 0; i < arg_value.size(); i++) {
    auto intrinsic_arg_type = f->getFunctionType()->getParamType(i);
    if (arg_value[i]->getType() != intrinsic_arg_type) {
      if (intrinsic_arg_type->isVectorTy()) {
        arg_value[i] = builder_->CreateBitCast(arg_value[i], intrinsic_arg_type);
      }
    }
  }

```

Then we call LLVM intrinsic function and could get the correct assembly.