This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCH][AArch64] PR84114: Avoid reassociating FMA
- From: James Greenhalgh <james dot greenhalgh at arm dot com>
- To: Wilco Dijkstra <Wilco dot Dijkstra at arm dot com>
- Cc: GCC Patches <gcc-patches at gcc dot gnu dot org>, nd <nd at arm dot com>, "sje at gcc dot gnu dot org" <sje at gcc dot gnu dot org>
- Date: Mon, 26 Feb 2018 22:25:45 +0000
- Subject: Re: [PATCH][AArch64] PR84114: Avoid reassociating FMA
- Authentication-results: sourceware.org; auth=none
- Authentication-results: spf=pass (sender IP is 217.140.96.140) smtp.mailfrom=arm.com; gcc.gnu.org; dkim=none (message not signed) header.d=none;gcc.gnu.org; dmarc=bestguesspass action=none header.from=arm.com;
- Nodisclaimer: True
- References: <DB6PR0801MB20536FBEAD77DF5C8B8490FF83CD0@DB6PR0801MB2053.eurprd08.prod.outlook.com>
- Spamdiagnosticmetadata: NSPM
- Spamdiagnosticoutput: 1:99
On Thu, Feb 22, 2018 at 11:38:03AM +0000, Wilco Dijkstra wrote:
> As discussed in the PR, the reassociation phase runs before FMAs are formed
> and so can significantly reduce FMA opportunities. Although reassociation
> could be switched off, it helps in many cases, so a better alternative is to
> only avoid reassociation of floating point additions. This fixes the testcase
> and gives 1% speedup on SPECFP2017, fixing the performance regression.
>
> OK for commit?
This is OK as a fairly safe fix for stage 4. We should fix reassociation
properly in GCC 9.
Thanks,
James
>
> ChangeLog:
> 2018-02-23 Wilco Dijkstra <wdijkstr@arm.com>
>
> PR tree-optimization/84114
> * config/aarch64/aarch64.c (aarch64_reassociation_width)
> Avoid reassociation of FLOAT_MODE addition.
> --
>
> diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
> index b3d5fde171920e5759046a4bd61cfcf9eb78d7dd..5f9541cf700aaf18c1f1ac73054614e2932781e4 100644
> --- a/gcc/config/aarch64/aarch64.c
> +++ b/gcc/config/aarch64/aarch64.c
> @@ -1109,15 +1109,16 @@ aarch64_min_divisions_for_recip_mul (machine_mode mode)
> return aarch64_tune_params.min_div_recip_mul_df;
> }
>
> +/* Return the reassociation width of treeop OPC with mode MODE. */
> static int
> -aarch64_reassociation_width (unsigned opc ATTRIBUTE_UNUSED,
> - machine_mode mode)
> +aarch64_reassociation_width (unsigned opc, machine_mode mode)
> {
> if (VECTOR_MODE_P (mode))
> return aarch64_tune_params.vec_reassoc_width;
> if (INTEGRAL_MODE_P (mode))
> return aarch64_tune_params.int_reassoc_width;
> - if (FLOAT_MODE_P (mode))
> + /* Avoid reassociating floating point addition so we emit more FMAs. */
> + if (FLOAT_MODE_P (mode) && opc != PLUS_EXPR)
> return aarch64_tune_params.fp_reassoc_width;
> return 1;
> }