Re: [PATCH v5 1/3] powerpc/bitops: Use immediate operand when possible

2021-12-07 Thread Michael Ellerman
On Tue, 21 Sep 2021 17:09:47 +0200, Christophe Leroy wrote: > Today we get the following code generation for bitops like > set or clear bit: > > c0009fe0: 39 40 08 00 li r10,2048 > c0009fe4: 7c e0 40 28 lwarx r7,0,r8 > c0009fe8: 7c e7 53 78 or

Re: [PATCH v5 1/3] powerpc/bitops: Use immediate operand when possible

2021-11-30 Thread Michael Ellerman
LEROY Christophe writes: > Hi Michael, > > Any chance to get this series merged this cycle ? Yeah. I hesitated a bit at the changes which make the atomic asm even more complicated, but I guess it's worth it. cheers > Le 21/09/2021 à 17:09, Christophe Leroy a écrit : >> Today we get the followin

Re: [PATCH v5 1/3] powerpc/bitops: Use immediate operand when possible

2021-11-26 Thread LEROY Christophe
Hi Michael, Any chance to get this series merged this cycle ? Thanks Christophe Le 21/09/2021 à 17:09, Christophe Leroy a écrit : > Today we get the following code generation for bitops like > set or clear bit: > > c0009fe0: 39 40 08 00 li r10,2048 > c0009fe4: 7

[PATCH v5 1/3] powerpc/bitops: Use immediate operand when possible

2021-09-21 Thread Christophe Leroy
Today we get the following code generation for bitops like set or clear bit: c0009fe0: 39 40 08 00 li r10,2048 c0009fe4: 7c e0 40 28 lwarx r7,0,r8 c0009fe8: 7c e7 53 78 or r7,r7,r10 c0009fec: 7c e0 41 2d stwcx. r7