public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
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 14/34] Import 'parity' functions from the CM0 library
Date: Mon, 31 Oct 2022 08:45:09 -0700	[thread overview]
Message-ID: <20221031154529.3627576-15-gnu@danielengel.com> (raw)
In-Reply-To: <20221031154529.3627576-1-gnu@danielengel.com>

The functional overlap between the single- and double-word functions makes
functions makes this implementation about half the size of the C functions
if both functions are linked in the same application.

gcc/libgcc/ChangeLog:
2022-10-09 Daniel Engel <gnu@danielengel.com>

	* config/arm/parity.S: New file for __paritysi2/di2().
	* config/arm/lib1funcs.S: #include bit/parity.S
	* config/arm/t-elf (LIB1ASMFUNCS): Added _paritysi2/di2.
---
 libgcc/config/arm/lib1funcs.S |   1 +
 libgcc/config/arm/parity.S    | 120 ++++++++++++++++++++++++++++++++++
 libgcc/config/arm/t-elf       |   2 +
 3 files changed, 123 insertions(+)
 create mode 100644 libgcc/config/arm/parity.S

diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S
index aa5957b8399..3f7b9e739f0 100644
--- a/libgcc/config/arm/lib1funcs.S
+++ b/libgcc/config/arm/lib1funcs.S
@@ -1704,6 +1704,7 @@ LSYM(Lover12):
 
 #include "clz2.S"
 #include "ctz2.S"
+#include "parity.S"
 
 /* ------------------------------------------------------------------------ */
 /* These next two sections are here despite the fact that they contain Thumb 
diff --git a/libgcc/config/arm/parity.S b/libgcc/config/arm/parity.S
new file mode 100644
index 00000000000..1405bea93a3
--- /dev/null
+++ b/libgcc/config/arm/parity.S
@@ -0,0 +1,120 @@
+/* parity.S: ARM optimized parity functions
+
+   Copyright (C) 2020-2022 Free Software Foundation, Inc.
+   Contributed by Daniel Engel (gnu@danielengel.com)
+
+   This file is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by the
+   Free Software Foundation; either version 3, or (at your option) any
+   later version.
+
+   This file is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+
+#ifdef L_paritydi2
+
+// int __paritydi2(int)
+// Returns '0' if the number of bits set in $r1:r0 is even, and '1' otherwise.
+// Returns the result in $r0.
+FUNC_START_SECTION paritydi2 .text.sorted.libgcc.paritydi2
+    CFI_START_FUNCTION
+
+        // Combine the upper and lower words, then fall through.
+        // Byte-endianness does not matter for this function.
+        eors    r0,     r1
+
+#endif /* L_paritydi2 */
+
+
+// The implementation of __paritydi2() tightly couples with __paritysi2(),
+//  such that instructions must appear consecutively in the same memory
+//  section for proper flow control.  However, this construction inhibits
+//  the ability to discard __paritydi2() when only using __paritysi2().
+// Therefore, this block configures __paritysi2() for compilation twice.
+// The first version is a minimal standalone implementation, and the second
+//  version is the continuation of __paritydi2().  The standalone version must
+//  be declared WEAK, so that the combined version can supersede it and
+//  provide both symbols when required.
+// '_paritysi2' should appear before '_paritydi2' in LIB1ASMFUNCS.
+#if defined(L_paritysi2) || defined(L_paritydi2)
+
+#ifdef L_paritysi2
+// int __paritysi2(int)
+// Returns '0' if the number of bits set in $r0 is even, and '1' otherwise.
+// Returns the result in $r0.
+// Uses $r2 as scratch space.
+WEAK_START_SECTION paritysi2 .text.sorted.libgcc.paritysi2
+    CFI_START_FUNCTION
+
+#else /* L_paritydi2 */
+FUNC_ENTRY paritysi2
+
+#endif
+
+  #if defined(__thumb__) && __thumb__
+    #if defined(__OPTIMIZE_SIZE__) && __OPTIMIZE_SIZE__
+
+        // Size optimized: 16 bytes, 40 cycles
+        // Speed optimized: 24 bytes, 14 cycles
+        movs    r2,     #16
+
+    LLSYM(__parity_loop):
+        // Calculate the parity of successively smaller half-words into the MSB.
+        movs    r1,     r0
+        lsls    r1,     r2
+        eors    r0,     r1
+        lsrs    r2,     #1
+        bne     LLSYM(__parity_loop)
+
+    #else /* !__OPTIMIZE_SIZE__ */
+
+        // Unroll the loop.  The 'libgcc' reference C implementation replaces
+        //  the x2 and the x1 shifts with a constant.  However, since it takes
+        //  4 cycles to load, index, and mask the constant result, it doesn't
+        //  cost anything to keep shifting (and saves a few bytes).
+        lsls    r1,     r0,     #16
+        eors    r0,     r1
+        lsls    r1,     r0,     #8
+        eors    r0,     r1
+        lsls    r1,     r0,     #4
+        eors    r0,     r1
+        lsls    r1,     r0,     #2
+        eors    r0,     r1
+        lsls    r1,     r0,     #1
+        eors    r0,     r1
+
+    #endif /* !__OPTIMIZE_SIZE__ */
+  #else /* !__thumb__ */
+
+        eors    r0,    r0,     r0,     lsl #16
+        eors    r0,    r0,     r0,     lsl #8
+        eors    r0,    r0,     r0,     lsl #4
+        eors    r0,    r0,     r0,     lsl #2
+        eors    r0,    r0,     r0,     lsl #1
+
+  #endif /* !__thumb__ */
+
+        lsrs    r0,     #31
+        RET
+
+    CFI_END_FUNCTION
+FUNC_END paritysi2
+
+#ifdef L_paritydi2
+FUNC_END paritydi2
+#endif
+
+#endif /* L_paritysi2 || L_paritydi2 */
+
diff --git a/libgcc/config/arm/t-elf b/libgcc/config/arm/t-elf
index 346fc766f17..0e9b9ce21af 100644
--- a/libgcc/config/arm/t-elf
+++ b/libgcc/config/arm/t-elf
@@ -24,6 +24,7 @@ endif # !__symbian__
 LIB1ASMFUNCS += \
         _clzsi2 \
 	_ctzsi2 \
+	_paritysi2 \
 
 
 # Group 1: Integer function objects.
@@ -37,6 +38,7 @@ LIB1ASMFUNCS += \
 	_ctzdi2 \
 	_ffssi2 \
 	_ffsdi2 \
+	_paritydi2 \
 	_dvmd_tls \
 	_divsi3 \
 	_modsi3 \
-- 
2.34.1


  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 ` Daniel Engel [this message]
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 ` [PATCH v7 18/34] Merge Thumb-2 optimizations for 64-bit comparison Daniel Engel
2022-10-31 15:45 ` [PATCH v7 19/34] Import 32-bit division from the CM0 library 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=20221031154529.3627576-15-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).