84 lines
2.6 KiB
Diff
84 lines
2.6 KiB
Diff
|
From bb211ae35474a9fa1a8189f0a4c525ce3d8c280e Mon Sep 17 00:00:00 2001
|
||
|
|
From: Jiahao Xu <xujiahao@loongson.cn>
|
||
|
|
Date: Wed, 6 Dec 2023 15:04:53 +0800
|
||
|
|
Subject: [PATCH 063/188] LoongArch: Vectorized loop unrolling is disable for
|
||
|
|
divf/sqrtf/rsqrtf when -mrecip is enabled.
|
||
|
|
|
||
|
|
Using -mrecip generates a sequence of instructions to replace divf, sqrtf and rsqrtf. The number
|
||
|
|
of generated instructions is close to or exceeds the maximum issue instructions per cycle of the
|
||
|
|
LoongArch, so vectorized loop unrolling is not performed on them.
|
||
|
|
|
||
|
|
gcc/ChangeLog:
|
||
|
|
|
||
|
|
* config/loongarch/loongarch.cc (loongarch_vector_costs::determine_suggested_unroll_factor):
|
||
|
|
If m_has_recip is true, uf return 1.
|
||
|
|
(loongarch_vector_costs::add_stmt_cost): Detect the use of approximate instruction sequence.
|
||
|
|
---
|
||
|
|
gcc/config/loongarch/loongarch.cc | 36 +++++++++++++++++++++++++++++--
|
||
|
|
1 file changed, 34 insertions(+), 2 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
|
||
|
|
index 18326ce47..d64777179 100644
|
||
|
|
--- a/gcc/config/loongarch/loongarch.cc
|
||
|
|
+++ b/gcc/config/loongarch/loongarch.cc
|
||
|
|
@@ -3970,7 +3970,9 @@ protected:
|
||
|
|
/* Reduction factor for suggesting unroll factor. */
|
||
|
|
unsigned m_reduc_factor = 0;
|
||
|
|
/* True if the loop contains an average operation. */
|
||
|
|
- bool m_has_avg =false;
|
||
|
|
+ bool m_has_avg = false;
|
||
|
|
+ /* True if the loop uses approximation instruction sequence. */
|
||
|
|
+ bool m_has_recip = false;
|
||
|
|
};
|
||
|
|
|
||
|
|
/* Implement TARGET_VECTORIZE_CREATE_COSTS. */
|
||
|
|
@@ -4017,7 +4019,7 @@ loongarch_vector_costs::determine_suggested_unroll_factor (loop_vec_info loop_vi
|
||
|
|
{
|
||
|
|
class loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
|
||
|
|
|
||
|
|
- if (m_has_avg)
|
||
|
|
+ if (m_has_avg || m_has_recip)
|
||
|
|
return 1;
|
||
|
|
|
||
|
|
/* Don't unroll if it's specified explicitly not to be unrolled. */
|
||
|
|
@@ -4077,6 +4079,36 @@ loongarch_vector_costs::add_stmt_cost (int count, vect_cost_for_stmt kind,
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
+ combined_fn cfn;
|
||
|
|
+ if (kind == vector_stmt
|
||
|
|
+ && stmt_info
|
||
|
|
+ && stmt_info->stmt)
|
||
|
|
+ {
|
||
|
|
+ /* Detect the use of approximate instruction sequence. */
|
||
|
|
+ if ((TARGET_RECIP_VEC_SQRT || TARGET_RECIP_VEC_RSQRT)
|
||
|
|
+ && (cfn = gimple_call_combined_fn (stmt_info->stmt)) != CFN_LAST)
|
||
|
|
+ switch (cfn)
|
||
|
|
+ {
|
||
|
|
+ case CFN_BUILT_IN_SQRTF:
|
||
|
|
+ m_has_recip = true;
|
||
|
|
+ default:
|
||
|
|
+ break;
|
||
|
|
+ }
|
||
|
|
+ else if (TARGET_RECIP_VEC_DIV
|
||
|
|
+ && gimple_code (stmt_info->stmt) == GIMPLE_ASSIGN)
|
||
|
|
+ {
|
||
|
|
+ machine_mode mode = TYPE_MODE (vectype);
|
||
|
|
+ switch (gimple_assign_rhs_code (stmt_info->stmt))
|
||
|
|
+ {
|
||
|
|
+ case RDIV_EXPR:
|
||
|
|
+ if (GET_MODE_INNER (mode) == SFmode)
|
||
|
|
+ m_has_recip = true;
|
||
|
|
+ default:
|
||
|
|
+ break;
|
||
|
|
+ }
|
||
|
|
+ }
|
||
|
|
+ }
|
||
|
|
+
|
||
|
|
return retval;
|
||
|
|
}
|
||
|
|
|
||
|
|
--
|
||
|
|
2.43.0
|
||
|
|
|