Displaying 6 results from an estimated 6 matches for "crscost".
Did you mean:
cricos
2017 Oct 27
2
Less aggressive on the first allocation of CSR if detecting an early exit
...bove, if a function has an early exit code, we
may want to be less aggressive on the first allocation of CSR in the entry
block by increasing the CSRCost.
Previously, I proposed https://reviews.llvm.org/D34608 in this matter, but
the way I detect the profitable cases and the way I increase the CRSCost was
somewhat unclear. Now, I'm thinking to less aggressive on the first
allocation of CSR in the entry block in case where the function has an early
exit so that encourage more shrink-wrapping and avoid executing CSR
spill/recover when the early exit is taken. By sending this out, I just want
t...
2017 Oct 30
2
Less aggressive on the first allocation of CSR if detecting an early exit
...want to be
>> less aggressive on the first allocation of CSR in the entry block by
>> increasing the CSRCost.
>>
>> Previously, I proposed https://reviews.llvm.org/D34608 in this
>> matter, but the way I detect the profitable cases and the way I
>> increase the CRSCost was somewhat unclear. Now, I'm thinking to less
>> aggressive on the first allocation of CSR in the entry block in case
>> where the function has an early exit so that encourage more
>> shrink-wrapping and avoid executing CSR spill/recover when the early
>> exit is taken...
2017 Oct 31
2
Less aggressive on the first allocation of CSR if detecting an early exit
...the first allocation of CSR in the entry block by
>>>> increasing the CSRCost.
>>>>
>>>> Previously, I proposed https://reviews.llvm.org/D34608 in this
>>>> matter, but the way I detect the profitable cases and the way I
>>>> increase the CRSCost was somewhat unclear. Now, I'm thinking to less
>>>> aggressive on the first allocation of CSR in the entry block in case
>>>> where the function has an early exit so that encourage more
>>>> shrink-wrapping and avoid executing CSR spill/recover when the earl...
2017 Nov 10
2
Less aggressive on the first allocation of CSR if detecting an early exit
...t to be
>> less aggressive on the first allocation of CSR in the entry block by
>> increasing the CSRCost.
>>
>> Previously, I proposed https://reviews.llvm.org/D34608 [1] in this
>> matter, but the way I detect the profitable cases and the way I
>> increase the CRSCost was somewhat unclear. Now, I'm thinking to less
>> aggressive on the first allocation of CSR in the entry block in case
>> where the function has an early exit so that encourage more
>> shrink-wrapping and avoid executing CSR spill/recover when the early
>> exit is taken...
2017 Nov 16
2
Less aggressive on the first allocation of CSR if detecting an early exit
...we may want to be
>> less aggressive on the first allocation of CSR in the entry block by
>> increasing the CSRCost.
>> Previously, I proposed https://reviews.llvm.org/D34608 [1] in this
>> matter, but the way I detect the profitable cases and the way I
>> increase the CRSCost was somewhat unclear. Now, I'm thinking to less
>> aggressive on the first allocation of CSR in the entry block in case
>> where the function has an early exit so that encourage more
>> shrink-wrapping and avoid executing CSR spill/recover when the early
>> exit is taken...
2017 Nov 17
2
Less aggressive on the first allocation of CSR if detecting an early exit
...we may want to be
>> less aggressive on the first allocation of CSR in the entry block by
>> increasing the CSRCost.
>> Previously, I proposed https://reviews.llvm.org/D34608 [1] in this
>> matter, but the way I detect the profitable cases and the way I
>> increase the CRSCost was somewhat unclear. Now, I'm thinking to less
>> aggressive on the first allocation of CSR in the entry block in case
>> where the function has an early exit so that encourage more
>> shrink-wrapping and avoid executing CSR spill/recover when the early
>> exit is taken...