From e2011ab13de3e70774f869b356f5f9c750780b34 Mon Sep 17 00:00:00 2001 From: Jan Hubicka Date: Tue, 15 Apr 2025 19:04:15 +0200 Subject: [PATCH] Set ADDSS cost to 3 for znver5 Znver5 has latency of addss 2 in typical case while all earlier versions has latency 3. Unforunately addss cost is used to cost many other SSE instructions than just addss and setting the cost to 2 makes us to vectorize 4 64bit stores into one 256bit store which in turn regesses imagemagick. This patch sets the cost back to 3. Next stage1 we can untie addss from the other operatoins and set it correctly. bootstrapped/regtested x86_64-linux and also benchmarked on SPEC2k17 gcc/ChangeLog: PR target/119298 * config/i386/x86-tune-costs.h (znver5_cost): Set ADDSS cost to 3. --- gcc/config/i386/x86-tune-costs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-costs.h index 7c8cb738d7c..9477345bdd7 100644 --- a/gcc/config/i386/x86-tune-costs.h +++ b/gcc/config/i386/x86-tune-costs.h @@ -2120,7 +2120,7 @@ struct processor_costs znver5_cost = { COSTS_N_INSNS (1), /* cost of cheap SSE instruction. */ /* ADDSS has throughput 2 and latency 2 (in some cases when source is another addition). */ - COSTS_N_INSNS (2), /* cost of ADDSS/SD SUBSS/SD insns. */ + COSTS_N_INSNS (3), /* cost of ADDSS/SD SUBSS/SD insns. */ /* MULSS has throughput 2 and latency 3. */ COSTS_N_INSNS (3), /* cost of MULSS instruction. */ COSTS_N_INSNS (3), /* cost of MULSD instruction. */