From: Daniel Engel <gnu@danielengel.com>
To: Richard Earnshaw <Richard.Earnshaw@foss.arm.com>,
gcc-patches@gcc.gnu.org
Cc: Daniel Engel <gnu@danielengel.com>,
Christophe Lyon <christophe.lyon@linaro.org>
Subject: [PATCH v7 18/34] Merge Thumb-2 optimizations for 64-bit comparison
Date: Mon, 31 Oct 2022 08:45:13 -0700 [thread overview]
Message-ID: <20221031154529.3627576-19-gnu@danielengel.com> (raw)
In-Reply-To: <20221031154529.3627576-1-gnu@danielengel.com>
This effectively merges support for all architecture variants into a
common function path with appropriate build conditions.
ARM performance is 1-2 instructions faster; Thumb-2 is about 50% faster.
gcc/libgcc/ChangeLog:
2022-10-09 Daniel Engel <gnu@danielengel.com>
* config/arm/bpabi.S (__aeabi_lcmp, __aeabi_ulcmp): Removed.
* config/arm/eabi/lcmp.S (__aeabi_lcmp, __aeabi_ulcmp): Added
conditional execution on supported architectures (__ARM_FEATURE_IT).
* config/arm/lib1funcs.S: Moved #include scope of eabi/lcmp.S.
---
libgcc/config/arm/bpabi.S | 42 -------------------------------
libgcc/config/arm/eabi/lcmp.S | 47 ++++++++++++++++++++++++++++++++++-
libgcc/config/arm/lib1funcs.S | 2 +-
3 files changed, 47 insertions(+), 44 deletions(-)
diff --git a/libgcc/config/arm/bpabi.S b/libgcc/config/arm/bpabi.S
index 17fe707ddf3..531a64fa98d 100644
--- a/libgcc/config/arm/bpabi.S
+++ b/libgcc/config/arm/bpabi.S
@@ -34,48 +34,6 @@
.eabi_attribute 25, 1
#endif /* __ARM_EABI__ */
-#ifdef L_aeabi_lcmp
-
-ARM_FUNC_START aeabi_lcmp
- cmp xxh, yyh
- do_it lt
- movlt r0, #-1
- do_it gt
- movgt r0, #1
- do_it ne
- RETc(ne)
- subs r0, xxl, yyl
- do_it lo
- movlo r0, #-1
- do_it hi
- movhi r0, #1
- RET
- FUNC_END aeabi_lcmp
-
-#endif /* L_aeabi_lcmp */
-
-#ifdef L_aeabi_ulcmp
-
-ARM_FUNC_START aeabi_ulcmp
- cmp xxh, yyh
- do_it lo
- movlo r0, #-1
- do_it hi
- movhi r0, #1
- do_it ne
- RETc(ne)
- cmp xxl, yyl
- do_it lo
- movlo r0, #-1
- do_it hi
- movhi r0, #1
- do_it eq
- moveq r0, #0
- RET
- FUNC_END aeabi_ulcmp
-
-#endif /* L_aeabi_ulcmp */
-
.macro test_div_by_zero signed
/* Tail-call to divide-by-zero handlers which may be overridden by the user,
so unwinding works properly. */
diff --git a/libgcc/config/arm/eabi/lcmp.S b/libgcc/config/arm/eabi/lcmp.S
index 99c7970ecba..d397325cbef 100644
--- a/libgcc/config/arm/eabi/lcmp.S
+++ b/libgcc/config/arm/eabi/lcmp.S
@@ -46,6 +46,19 @@ FUNC_START_SECTION LCMP_NAME LCMP_SECTION
subs xxl, yyl
sbcs xxh, yyh
+ #ifdef __HAVE_FEATURE_IT
+ do_it lt,t
+
+ #ifdef L_aeabi_lcmp
+ movlt r0, #-1
+ #else
+ movlt r0, #0
+ #endif
+
+ // Early return on '<'.
+ RETc(lt)
+
+ #else /* !__HAVE_FEATURE_IT */
// With $r2 free, create a known offset value without affecting
// the N or Z flags.
// BUG? The originally unified instruction for v6m was 'mov r2, r3'.
@@ -62,17 +75,27 @@ FUNC_START_SECTION LCMP_NAME LCMP_SECTION
// argument is larger, otherwise the offset value remains 0.
adds r2, #2
+ #endif
+
// Check for zero (equality in 64 bits).
// It doesn't matter which register was originally "hi".
orrs r0, r1
+ #ifdef __HAVE_FEATURE_IT
+ // The result is already 0 on equality.
+ // -1 already returned, so just force +1.
+ do_it ne
+ movne r0, #1
+
+ #else /* !__HAVE_FEATURE_IT */
// The result is already 0 on equality.
beq LLSYM(__lcmp_return)
- LLSYM(__lcmp_lt):
+ LLSYM(__lcmp_lt):
// Create +1 or -1 from the offset value defined earlier.
adds r3, #1
subs r0, r2, r3
+ #endif
LLSYM(__lcmp_return):
#ifdef L_cmpdi2
@@ -111,21 +134,43 @@ FUNC_START_SECTION ULCMP_NAME ULCMP_SECTION
subs xxl, yyl
sbcs xxh, yyh
+ #ifdef __HAVE_FEATURE_IT
+ do_it lo,t
+
+ #ifdef L_aeabi_ulcmp
+ movlo r0, -1
+ #else
+ movlo r0, #0
+ #endif
+
+ // Early return on '<'.
+ RETc(lo)
+
+ #else
// Capture the carry flg.
// $r2 will contain -1 if the first value is smaller,
// 0 if the first value is larger or equal.
sbcs r2, r2
+ #endif
// Check for zero (equality in 64 bits).
// It doesn't matter which register was originally "hi".
orrs r0, r1
+ #ifdef __HAVE_FEATURE_IT
+ // The result is already 0 on equality.
+ // -1 already returned, so just force +1.
+ do_it ne
+ movne r0, #1
+
+ #else /* !__HAVE_FEATURE_IT */
// The result is already 0 on equality.
beq LLSYM(__ulcmp_return)
// Assume +1. If -1 is correct, $r2 will override.
movs r0, #1
orrs r0, r2
+ #endif
LLSYM(__ulcmp_return):
#ifdef L_ucmpdi2
diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S
index d85a20252d9..796f6f30ed9 100644
--- a/libgcc/config/arm/lib1funcs.S
+++ b/libgcc/config/arm/lib1funcs.S
@@ -1991,6 +1991,6 @@ LSYM(Lchange_\register):
#include "bpabi.S"
#else /* NOT_ISA_TARGET_32BIT */
#include "bpabi-v6m.S"
-#include "eabi/lcmp.S"
#endif /* NOT_ISA_TARGET_32BIT */
+#include "eabi/lcmp.S"
#endif /* !__symbian__ */
--
2.34.1
next prev parent reply other threads:[~2022-10-31 15:47 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-31 15:44 [PATCH v7 00/34] libgcc: Thumb-1 Floating-Point Assembly for Cortex M0 Daniel Engel
2022-10-31 15:44 ` [PATCH v7 01/34] Add and restructure function declaration macros Daniel Engel
2022-10-31 15:44 ` [PATCH v7 02/34] Rename THUMB_FUNC_START to THUMB_FUNC_ENTRY Daniel Engel
2022-10-31 15:44 ` [PATCH v7 03/34] Fix syntax warnings on conditional instructions Daniel Engel
2022-10-31 15:44 ` [PATCH v7 04/34] Reorganize LIB1ASMFUNCS object wrapper macros Daniel Engel
2022-10-31 15:45 ` [PATCH v7 05/34] Add the __HAVE_FEATURE_IT and IT() macros Daniel Engel
2022-10-31 15:45 ` [PATCH v7 06/34] Refactor 'clz' functions into a new file Daniel Engel
2022-10-31 15:45 ` [PATCH v7 07/34] Refactor 'ctz' " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 08/34] Refactor 64-bit shift " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 09/34] Import 'clz' functions from the CM0 library Daniel Engel
2022-10-31 15:45 ` [PATCH v7 10/34] Import 'ctz' " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 11/34] Import 64-bit shift " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 12/34] Import 'clrsb' " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 13/34] Import 'ffs' " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 14/34] Import 'parity' " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 15/34] Import 'popcnt' " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 16/34] Refactor Thumb-1 64-bit comparison into a new file Daniel Engel
2022-10-31 15:45 ` [PATCH v7 17/34] Import 64-bit comparison from CM0 library Daniel Engel
2022-10-31 15:45 ` Daniel Engel [this message]
2022-10-31 15:45 ` [PATCH v7 19/34] Import 32-bit division from the " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 20/34] Refactor Thumb-1 64-bit division into a new file Daniel Engel
2022-10-31 15:45 ` [PATCH v7 21/34] Import 64-bit division from the CM0 library Daniel Engel
2022-10-31 15:45 ` [PATCH v7 22/34] Import integer multiplication " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 23/34] Refactor Thumb-1 float comparison into a new file Daniel Engel
2022-10-31 15:45 ` [PATCH v7 24/34] Import float comparison from the CM0 library Daniel Engel
2022-10-31 15:45 ` [PATCH v7 25/34] Refactor Thumb-1 float subtraction into a new file Daniel Engel
2022-10-31 15:45 ` [PATCH v7 26/34] Import float addition and subtraction from the CM0 library Daniel Engel
2022-10-31 15:45 ` [PATCH v7 27/34] Import float multiplication " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 28/34] Import float division " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 29/34] Import integer-to-float conversion " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 30/34] Import float-to-integer " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 31/34] Import float<->double " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 32/34] Import float<->__fp16 " Daniel Engel
2022-10-31 15:45 ` [PATCH v7 33/34] Drop single-precision Thumb-1 soft-float functions Daniel Engel
2022-10-31 15:45 ` [PATCH v7 34/34] Add -mpure-code support to the CM0 functions Daniel Engel
2022-11-15 15:27 ` [PING] Re: [PATCH v7 00/34] libgcc: Thumb-1 Floating-Point Assembly for Cortex M0 Daniel Engel
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20221031154529.3627576-19-gnu@danielengel.com \
--to=gnu@danielengel.com \
--cc=Richard.Earnshaw@foss.arm.com \
--cc=christophe.lyon@linaro.org \
--cc=gcc-patches@gcc.gnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).