llvm dev - Nov 2011 - [LLVMdev] llvm_anyint_ty clarification

Hello everyone,

I am trying to implement the max PTX builtin function.
This is defined in the following way:

"max.type   d, a, b;"

where .type can be:
.type = { .u16, .u32, .u64,
                .s16, .s32, .s64 };

The presence of multiple types requires llvm.ptx.max
to be overloaded for i16, i32 and i64.
So I think that the right way to define the intrinsic would be
(as in the attached max_not_working.patch file):

def int_ptx_max : Intrinsic<[llvm_anyint_ty],
                            [LLVMMatchType<0>, LLVMMatchType<0>],
                            [Commutative]>;

The problem is that the builtin is not recognised in the following test case:

define ptx_device i16 @max_16(i16 %a, i16 %b) {
entry:
  %d = call i16 @llvm.ptx.max(i16 %a, i16 %b)
  ret i16 %d
}
declare i16 @llvm.ptx.max(i16, i16)

Things change if I define explicitly the i16 intrinsic, like this:

def int_ptx_max : Intrinsic<[llvm_i16_ty],
                            [llvm_i16_ty, llvm_i16_ty],
                            [Commutative]>;
In this case all goes well. But this is obviously non-extensible.

Am I using the llvm_anyint_ty type in the right way ?
Is there another way to implement this kind of behaviour?

Thanks,

Alberto
-------------- next part --------------
A non-text attachment was scrubbed...
Name: max_not_working.patch
Type: text/x-patch
Size: 1347 bytes
Desc: not available
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20111119/c9cac7e2/attachment.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: max_working.patch
Type: text/x-patch
Size: 1334 bytes
Desc: not available
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20111119/c9cac7e2/attachment-0001.bin>

On Sat, Nov 19, 2011 at 10:13 AM, Alberto Magni
<alberto.magni86 at gmail.com> wrote:
> Hello everyone,
>
> I am trying to implement the max PTX builtin function.
> This is defined in the following way:
>
> "max.type   d, a, b;"
>
> where .type can be:
> .type = { .u16, .u32, .u64,
>                .s16, .s32, .s64 };
>
> The presence of multiple types requires llvm.ptx.max
> to be overloaded for i16, i32 and i64.
> So I think that the right way to define the intrinsic would be
> (as in the attached max_not_working.patch file):
>
> def int_ptx_max : Intrinsic<[llvm_anyint_ty],
>                            [LLVMMatchType<0>,
LLVMMatchType<0>],
>                            [Commutative]>;
>
> The problem is that the builtin is not recognised in the following test
case:
>
> define ptx_device i16 @max_16(i16 %a, i16 %b) {
> entry:
>  %d = call i16 @llvm.ptx.max(i16 %a, i16 %b)
>  ret i16 %d
> }
> declare i16 @llvm.ptx.max(i16, i16)
Try llvm.ptx.max.i16.

-Eli