Displaying 5 results from an estimated 5 matches for "fc_long".
2009 Oct 13
4
[LLVMdev] 65bit integer math
I have a test case(attached as fc_long.ll) that when run through the
optimizer produces 65bit integer math(fc_long-opt.ll).
Now I understand that llvm can have any length integer, but I consider
turning a 64bit mul into multiple 65 bit instructions to be a 'bad'
optimization. This eventually expands to a 128bit multiply
call...
2009 Oct 13
3
[LLVMdev] 65bit integer math
On Mon, Oct 12, 2009 at 8:22 PM, Eli Friedman <eli.friedman at gmail.com> wrote:
> On Mon, Oct 12, 2009 at 6:15 PM, Villmow, Micah <Micah.Villmow at amd.com> wrote:
>> I have a test case(attached as fc_long.ll) that when run through the
>> optimizer produces 65bit integer math(fc_long-opt.ll).
>>
>>
>>
>> Now I understand that llvm can have any length integer, but I consider
>> turning a 64bit mul into multiple 65 bit instructions to be a ‘bad’
>> optimization...
2009 Oct 13
0
[LLVMdev] 65bit integer math
On Mon, Oct 12, 2009 at 6:15 PM, Villmow, Micah <Micah.Villmow at amd.com> wrote:
> I have a test case(attached as fc_long.ll) that when run through the
> optimizer produces 65bit integer math(fc_long-opt.ll).
>
>
>
> Now I understand that llvm can have any length integer, but I consider
> turning a 64bit mul into multiple 65 bit instructions to be a ‘bad’
> optimization. This eventually expands to...
2009 Oct 13
0
[LLVMdev] 65bit integer math
...ct 12, 2009, at 9:42 PM, Jeffrey Yasskin wrote:
> On Mon, Oct 12, 2009 at 8:22 PM, Eli Friedman
> <eli.friedman at gmail.com> wrote:
>> On Mon, Oct 12, 2009 at 6:15 PM, Villmow, Micah <Micah.Villmow at amd.com
>> > wrote:
>>> I have a test case(attached as fc_long.ll) that when run through the
>>> optimizer produces 65bit integer math(fc_long-opt.ll).
>>>
>>>
>>>
>>> Now I understand that llvm can have any length integer, but I
>>> consider
>>> turning a 64bit mul into multiple 65 bit instructi...
2009 Oct 13
2
[LLVMdev] 65bit integer math
...ct 12, 2009, at 9:42 PM, Jeffrey Yasskin wrote:
> On Mon, Oct 12, 2009 at 8:22 PM, Eli Friedman
> <eli.friedman at gmail.com> wrote:
>> On Mon, Oct 12, 2009 at 6:15 PM, Villmow, Micah
<Micah.Villmow at amd.com
>> > wrote:
>>> I have a test case(attached as fc_long.ll) that when run through the
>>> optimizer produces 65bit integer math(fc_long-opt.ll).
>>>
>>>
>>>
>>> Now I understand that llvm can have any length integer, but I
>>> consider
>>> turning a 64bit mul into multiple 65 bit instructi...