From d7f0bc05949481048d2fd524ecb2d892f6a04294 Mon Sep 17 00:00:00 2001
From: Hans-Peter Nilsson <hp@axis.com>
Date: Thu, 27 Apr 2023 02:00:33 +0200
Subject: [PATCH] libgcc CRIS: Define TARGET_HAS_NO_HW_DIVIDE

With this, execution time for e.g. __moddi3 go from 59 to 40 cycles in
the "fast" case or from 290 to 200 cycles in the "slow" case (when the
!TARGET_HAS_NO_HW_DIVIDE variant calls division and modulus functions
for 32-bit SImode), as exposed by gcc.c-torture/execute/arith-rand-ll.c
compiled for -march=v10.

Unfortunately, it just puts a performance improvement "dent" of 0.07%
in a arith-rand-ll.c-based performance test - where all loops are also
reduced to 1/10.

The size of every affected libgcc function is reduced to less than
half and they are all now leaf functions.

	* config/cris/t-cris (HOST_LIBGCC2_CFLAGS): Add
	-DTARGET_HAS_NO_HW_DIVIDE.
---
 libgcc/config/cris/t-cris | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/libgcc/config/cris/t-cris b/libgcc/config/cris/t-cris
index b582974a42ee..e0020294be96 100644
--- a/libgcc/config/cris/t-cris
+++ b/libgcc/config/cris/t-cris
@@ -8,3 +8,6 @@ $(LIB2ADD): $(srcdir)/config/cris/arit.c
 	echo "#define L$$name" > tmp-$@ \
 	&& echo '#include "$<"' >> tmp-$@ \
 	&& mv -f tmp-$@ $@
+
+# Use an appropriate implementation when implementing DImode division.
+HOST_LIBGCC2_CFLAGS += -DTARGET_HAS_NO_HW_DIVIDE
-- 
GitLab