Re: [PATCH][AArch64] Improve legitimize_address

2016-09-08 Thread Wilco Dijkstra
Christophe Lyon wrote: > After this patch, I've noticed a regression: > FAIL: gcc.target/aarch64/ldp_vec_64_1.c scan-assembler ldp\td[0-9]+, d[0-9] > You probably need to adjust the scan pattern. The original code was better and what we should generate. IVOpt chooses to use indexing eventhough it

Re: [PATCH][AArch64] Improve legitimize_address

2016-09-07 Thread Christophe Lyon
Hi Wilco, On 7 September 2016 at 14:43, Richard Earnshaw (lists) wrote: > On 06/09/16 14:14, Wilco Dijkstra wrote: >> Improve aarch64_legitimize_address - avoid splitting the offset if it is >> supported. When we do split, take the mode size into account. BLKmode >>

Re: [PATCH][AArch64] Improve legitimize_address

2016-09-07 Thread Richard Earnshaw (lists)
On 06/09/16 14:14, Wilco Dijkstra wrote: > Improve aarch64_legitimize_address - avoid splitting the offset if it is > supported. When we do split, take the mode size into account. BLKmode > falls into the unaligned case but should be treated like LDP/STP. > This improves codesize slightly due to

[PATCH][AArch64] Improve legitimize_address

2016-09-06 Thread Wilco Dijkstra
Improve aarch64_legitimize_address - avoid splitting the offset if it is supported. When we do split, take the mode size into account. BLKmode falls into the unaligned case but should be treated like LDP/STP. This improves codesize slightly due to fewer base address calculations: int f(int *p)