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 22/34] Import integer multiplication from the CM0 library
Date: Mon, 31 Oct 2022 08:45:17 -0700 [thread overview]
Message-ID: <20221031154529.3627576-23-gnu@danielengel.com> (raw)
In-Reply-To: <20221031154529.3627576-1-gnu@danielengel.com>
gcc/libgcc/ChangeLog:
2022-10-09 Daniel Engel <gnu@danielengel.com>
* config/arm/eabi/lmul.S: New file for __muldi3(), __mulsidi3(), and
__umulsidi3().
* config/arm/lib1funcs.S: #eabi/lmul.S (v6m only).
* config/arm/t-elf: Add the new objects to LIB1ASMFUNCS.
---
libgcc/config/arm/eabi/lmul.S | 218 ++++++++++++++++++++++++++++++++++
libgcc/config/arm/lib1funcs.S | 1 +
libgcc/config/arm/t-elf | 13 +-
3 files changed, 230 insertions(+), 2 deletions(-)
create mode 100644 libgcc/config/arm/eabi/lmul.S
diff --git a/libgcc/config/arm/eabi/lmul.S b/libgcc/config/arm/eabi/lmul.S
new file mode 100644
index 00000000000..377e571bf09
--- /dev/null
+++ b/libgcc/config/arm/eabi/lmul.S
@@ -0,0 +1,218 @@
+/* lmul.S: Thumb-1 optimized 64-bit integer multiplication
+
+ Copyright (C) 2018-2022 Free Software Foundation, Inc.
+ Contributed by Daniel Engel, Senva Inc (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_muldi3
+
+// long long __aeabi_lmul(long long, long long)
+// Returns the least significant 64 bits of a 64 bit multiplication.
+// Expects the two multiplicands in $r1:$r0 and $r3:$r2.
+// Returns the product in $r1:$r0 (does not distinguish signed types).
+// Uses $r4 and $r5 as scratch space.
+// Same parent section as __umulsidi3() to keep tail call branch within range.
+FUNC_START_SECTION muldi3 .text.sorted.libgcc.lmul.muldi3
+
+#ifndef __symbian__
+ FUNC_ALIAS aeabi_lmul muldi3
+#endif
+
+ CFI_START_FUNCTION
+
+ // $r1:$r0 = 0xDDDDCCCCBBBBAAAA
+ // $r3:$r2 = 0xZZZZYYYYXXXXWWWW
+
+ // The following operations that only affect the upper 64 bits
+ // can be safely discarded:
+ // DDDD * ZZZZ
+ // DDDD * YYYY
+ // DDDD * XXXX
+ // CCCC * ZZZZ
+ // CCCC * YYYY
+ // BBBB * ZZZZ
+
+ // MAYBE: Test for multiply by ZERO on implementations with a 32-cycle
+ // 'muls' instruction, and skip over the operation in that case.
+
+ // (0xDDDDCCCC * 0xXXXXWWWW), free $r1
+ muls xxh, yyl
+
+ // (0xZZZZYYYY * 0xBBBBAAAA), free $r3
+ muls yyh, xxl
+ adds yyh, xxh
+
+ // Put the parameters in the correct form for umulsidi3().
+ movs xxh, yyl
+ b LLSYM(__mul_overflow)
+
+ CFI_END_FUNCTION
+FUNC_END muldi3
+
+#ifndef __symbian__
+ FUNC_END aeabi_lmul
+#endif
+
+#endif /* L_muldi3 */
+
+
+// The following implementation of __umulsidi3() integrates with __muldi3()
+// above to allow the fast tail call while still preserving the extra
+// hi-shifted bits of the result. However, these extra bits add a few
+// instructions not otherwise required when using only __umulsidi3().
+// Therefore, this block configures __umulsidi3() for compilation twice.
+// The first version is a minimal standalone implementation, and the second
+// version adds the hi bits of __muldi3(). The standalone version must
+// be declared WEAK, so that the combined version can supersede it and
+// provide both symbols in programs that multiply long doubles.
+// This means '_umulsidi3' should appear before '_muldi3' in LIB1ASMFUNCS.
+#if defined(L_muldi3) || defined(L_umulsidi3)
+
+#ifdef L_umulsidi3
+// unsigned long long __umulsidi3(unsigned int, unsigned int)
+// Returns all 64 bits of a 32 bit multiplication.
+// Expects the two multiplicands in $r0 and $r1.
+// Returns the product in $r1:$r0.
+// Uses $r3, $r4 and $ip as scratch space.
+WEAK_START_SECTION umulsidi3 .text.sorted.libgcc.lmul.umulsidi3
+ CFI_START_FUNCTION
+
+#else /* L_muldi3 */
+FUNC_ENTRY umulsidi3
+ CFI_START_FUNCTION
+
+ // 32x32 multiply with 64 bit result.
+ // Expand the multiply into 4 parts, since muls only returns 32 bits.
+ // (a16h * b16h / 2^32)
+ // + (a16h * b16l / 2^48) + (a16l * b16h / 2^48)
+ // + (a16l * b16l / 2^64)
+
+ // MAYBE: Test for multiply by 0 on implementations with a 32-cycle
+ // 'muls' instruction, and skip over the operation in that case.
+
+ eors yyh, yyh
+
+ LLSYM(__mul_overflow):
+ mov ip, yyh
+
+#endif /* !L_muldi3 */
+
+ // a16h * b16h
+ lsrs r2, xxl, #16
+ lsrs r3, xxh, #16
+ muls r2, r3
+
+ #ifdef L_muldi3
+ add ip, r2
+ #else
+ mov ip, r2
+ #endif
+
+ // a16l * b16h; save a16h first!
+ lsrs r2, xxl, #16
+ #if (__ARM_ARCH >= 6)
+ uxth xxl, xxl
+ #else /* __ARM_ARCH < 6 */
+ lsls xxl, #16
+ lsrs xxl, #16
+ #endif
+ muls r3, xxl
+
+ // a16l * b16l
+ #if (__ARM_ARCH >= 6)
+ uxth xxh, xxh
+ #else /* __ARM_ARCH < 6 */
+ lsls xxh, #16
+ lsrs xxh, #16
+ #endif
+ muls xxl, xxh
+
+ // a16h * b16l
+ muls xxh, r2
+
+ // Distribute intermediate results.
+ eors r2, r2
+ adds xxh, r3
+ adcs r2, r2
+ lsls r3, xxh, #16
+ lsrs xxh, #16
+ lsls r2, #16
+ adds xxl, r3
+ adcs xxh, r2
+
+ // Add in the high bits.
+ add xxh, ip
+
+ RET
+
+ CFI_END_FUNCTION
+FUNC_END umulsidi3
+
+#endif /* L_muldi3 || L_umulsidi3 */
+
+
+#ifdef L_mulsidi3
+
+// long long mulsidi3(int, int)
+// Returns all 64 bits of a 32 bit signed multiplication.
+// Expects the two multiplicands in $r0 and $r1.
+// Returns the product in $r1:$r0.
+// Uses $r3, $r4 and $rT as scratch space.
+FUNC_START_SECTION mulsidi3 .text.sorted.libgcc.lmul.mulsidi3
+ CFI_START_FUNCTION
+
+ // Push registers for function call.
+ push { rT, lr }
+ .cfi_remember_state
+ .cfi_adjust_cfa_offset 8
+ .cfi_rel_offset rT, 0
+ .cfi_rel_offset lr, 4
+
+ // Save signs of the arguments.
+ asrs r3, r0, #31
+ asrs rT, r1, #31
+
+ // Absolute value of the arguments.
+ eors r0, r3
+ eors r1, rT
+ subs r0, r3
+ subs r1, rT
+
+ // Save sign of the result.
+ eors rT, r3
+
+ bl SYM(__umulsidi3) __PLT__
+
+ // Apply sign of the result.
+ eors xxl, rT
+ eors xxh, rT
+ subs xxl, rT
+ sbcs xxh, rT
+
+ pop { rT, pc }
+ .cfi_restore_state
+
+ CFI_END_FUNCTION
+FUNC_END mulsidi3
+
+#endif /* L_mulsidi3 */
+
diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S
index 51fb32e38aa..e828d53d732 100644
--- a/libgcc/config/arm/lib1funcs.S
+++ b/libgcc/config/arm/lib1funcs.S
@@ -1578,6 +1578,7 @@ LSYM(Lover12):
#define PEDANTIC_DIV0 (1)
#include "eabi/idiv.S"
#include "eabi/ldiv.S"
+#include "eabi/lmul.S"
#endif /* NOT_ISA_TARGET_32BIT */
/* ------------------------------------------------------------------------ */
diff --git a/libgcc/config/arm/t-elf b/libgcc/config/arm/t-elf
index 4d430325fa1..eb1acd8d5a2 100644
--- a/libgcc/config/arm/t-elf
+++ b/libgcc/config/arm/t-elf
@@ -27,6 +27,13 @@ LIB1ASMFUNCS += \
_paritysi2 \
_popcountsi2 \
+ifeq (__ARM_ARCH_ISA_THUMB 1,$(ARM_ISA)$(THUMB1_ISA))
+# Group 0B: WEAK overridable function objects built for v6m only.
+LIB1ASMFUNCS += \
+ _muldi3 \
+
+endif
+
# Group 1: Integer function objects.
LIB1ASMFUNCS += \
@@ -51,11 +58,13 @@ LIB1ASMFUNCS += \
ifeq (__ARM_ARCH_ISA_THUMB 1,$(ARM_ISA)$(THUMB1_ISA))
-# Group 1B: Integer functions built for v6m only.
+# Group 1B: Integer function objects built for v6m only.
LIB1ASMFUNCS += \
_divdi3 \
_udivdi3 \
-
+ _mulsidi3 \
+ _umulsidi3 \
+
endif
--
2.34.1
next prev parent reply other threads:[~2022-10-31 15:48 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 ` [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 ` Daniel Engel [this message]
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=20221031154529.3627576-23-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).