From 3e27ea26fedf00c2662d8460cdf6aca05d0d64aa Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Wed, 28 Aug 2024 16:41:08 +0100
Subject: [PATCH] aarch64: Fix gather x32/x64 selection
The SVE gather and scatter costs are classified based on whether
they do 4 loads per 128 bits (x32) or 2 loads per 128 bits (x64).
The number after the "x" refers to the number of bits in each
"container".
However, the test for which to use was based on the element size
rather than the container size. This meant that we'd use the
overly conservative x32 costs for VNx2SI gathers. VNx2SI gathers
are really .D gathers in which the upper half of each extension
result is ignored.
This patch is necessary to switch -mtune=generic over to the
"new" vector costs.
gcc/
* config/aarch64/aarch64.cc (aarch64_detect_vector_stmt_subtype)
(aarch64_vector_costs::add_stmt_cost): Use the x64 cost rather
than x32 cost for all VNx2 modes.
---
gcc/config/aarch64/aarch64.cc | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 40dacfcf2e78..033ea61d3a8e 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -16819,7 +16819,8 @@ aarch64_detect_vector_stmt_subtype (vec_info *vinfo, vect_cost_for_stmt kind,
&& STMT_VINFO_MEMORY_ACCESS_TYPE (stmt_info) == VMAT_GATHER_SCATTER)
{
unsigned int nunits = vect_nunits_for_cost (vectype);
- if (GET_MODE_UNIT_BITSIZE (TYPE_MODE (vectype)) == 64)
+ /* Test for VNx2 modes, which have 64-bit containers. */
+ if (known_eq (GET_MODE_NUNITS (TYPE_MODE (vectype)), aarch64_sve_vg))
return { sve_costs->gather_load_x64_cost, nunits };
return { sve_costs->gather_load_x32_cost, nunits };
}
@@ -17309,7 +17310,9 @@ aarch64_vector_costs::add_stmt_cost (int count, vect_cost_for_stmt kind,
const sve_vec_cost *sve_costs = aarch64_tune_params.vec_costs->sve;
if (sve_costs)
{
- if (GET_MODE_UNIT_BITSIZE (TYPE_MODE (vectype)) == 64)
+ /* Test for VNx2 modes, which have 64-bit containers. */
+ if (known_eq (GET_MODE_NUNITS (TYPE_MODE (vectype)),
+ aarch64_sve_vg))
m_sve_gather_scatter_init_cost
+= sve_costs->gather_load_x64_init_cost;
else
--
GitLab