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 09/34] Import 'clz' functions from the CM0 library
Date: Mon, 31 Oct 2022 08:45:04 -0700 [thread overview]
Message-ID: <20221031154529.3627576-10-gnu@danielengel.com> (raw)
In-Reply-To: <20221031154529.3627576-1-gnu@danielengel.com>
On architectures without __ARM_FEATURE_CLZ, this version combines __clzdi2()
with __clzsi2() into a single object with an efficient tail call. Also, this
version merges the formerly separate Thumb and ARM code implementations
into a unified instruction sequence. This change significantly improves
Thumb performance without affecting ARM performance. Finally, this version
adds a new __OPTIMIZE_SIZE__ build option (binary search loop).
There is no change to the code for architectures with __ARM_FEATURE_CLZ.
gcc/libgcc/ChangeLog:
2022-10-09 Daniel Engel <gnu@danielengel.com>
* config/arm/bits/clz2.S (__clzsi2, __clzdi2): Reduced code size on
architectures without __ARM_FEATURE_CLZ.
* config/arm/t-elf (LIB1ASMFUNCS): Moved _clzsi2 to new weak roup.
---
libgcc/config/arm/clz2.S | 363 +++++++++++++++++++++++++--------------
libgcc/config/arm/t-elf | 7 +-
2 files changed, 237 insertions(+), 133 deletions(-)
diff --git a/libgcc/config/arm/clz2.S b/libgcc/config/arm/clz2.S
index 439341752ba..ed04698fef4 100644
--- a/libgcc/config/arm/clz2.S
+++ b/libgcc/config/arm/clz2.S
@@ -1,145 +1,244 @@
-/* Copyright (C) 1995-2022 Free Software Foundation, Inc.
+/* clz2.S: Cortex M0 optimized 'clz' functions
-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.
+ Copyright (C) 2018-2022 Free Software Foundation, Inc.
+ Contributed by Daniel Engel (gnu@danielengel.com)
-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.
+ 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.
-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.
+ 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.
-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/>. */
+ 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/>. */
+
+
+#if defined(__ARM_FEATURE_CLZ) && __ARM_FEATURE_CLZ
+
+#ifdef L_clzdi2
+
+// int __clzdi2(long long)
+// Counts leading zero bits in $r1:$r0.
+// Returns the result in $r0.
+FUNC_START_SECTION clzdi2 .text.sorted.libgcc.clz2.clzdi2
+ CFI_START_FUNCTION
+
+ // Moved here from lib1funcs.S
+ cmp xxh, #0
+ do_it eq, et
+ clzeq r0, xxl
+ clzne r0, xxh
+ addeq r0, #32
+ RET
+
+ CFI_END_FUNCTION
+FUNC_END clzdi2
+
+#endif /* L_clzdi2 */
#ifdef L_clzsi2
-#ifdef NOT_ISA_TARGET_32BIT
-FUNC_START clzsi2
- movs r1, #28
- movs r3, #1
- lsls r3, r3, #16
- cmp r0, r3 /* 0x10000 */
- bcc 2f
- lsrs r0, r0, #16
- subs r1, r1, #16
-2: lsrs r3, r3, #8
- cmp r0, r3 /* #0x100 */
- bcc 2f
- lsrs r0, r0, #8
- subs r1, r1, #8
-2: lsrs r3, r3, #4
- cmp r0, r3 /* #0x10 */
- bcc 2f
- lsrs r0, r0, #4
- subs r1, r1, #4
-2: adr r2, 1f
- ldrb r0, [r2, r0]
- adds r0, r0, r1
- bx lr
-.align 2
-1:
-.byte 4, 3, 2, 2, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0
- FUNC_END clzsi2
-#else
-ARM_FUNC_START clzsi2
-# if defined (__ARM_FEATURE_CLZ)
- clz r0, r0
- RET
-# else
- mov r1, #28
- cmp r0, #0x10000
- do_it cs, t
- movcs r0, r0, lsr #16
- subcs r1, r1, #16
- cmp r0, #0x100
- do_it cs, t
- movcs r0, r0, lsr #8
- subcs r1, r1, #8
- cmp r0, #0x10
- do_it cs, t
- movcs r0, r0, lsr #4
- subcs r1, r1, #4
- adr r2, 1f
- ldrb r0, [r2, r0]
- add r0, r0, r1
- RET
-.align 2
-1:
-.byte 4, 3, 2, 2, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0
-# endif /* !defined (__ARM_FEATURE_CLZ) */
- FUNC_END clzsi2
-#endif
+
+// int __clzsi2(int)
+// Counts leading zero bits in $r0.
+// Returns the result in $r0.
+FUNC_START_SECTION clzsi2 .text.sorted.libgcc.clz2.clzsi2
+ CFI_START_FUNCTION
+
+ // Moved here from lib1funcs.S
+ clz r0, r0
+ RET
+
+ CFI_END_FUNCTION
+FUNC_END clzsi2
+
#endif /* L_clzsi2 */
+#else /* !__ARM_FEATURE_CLZ */
+
#ifdef L_clzdi2
-#if !defined (__ARM_FEATURE_CLZ)
-
-# ifdef NOT_ISA_TARGET_32BIT
-FUNC_START clzdi2
- push {r4, lr}
- cmp xxh, #0
- bne 1f
-# ifdef __ARMEB__
- movs r0, xxl
- bl __clzsi2
- adds r0, r0, #32
- b 2f
-1:
- bl __clzsi2
-# else
- bl __clzsi2
- adds r0, r0, #32
- b 2f
-1:
- movs r0, xxh
- bl __clzsi2
-# endif
-2:
- pop {r4, pc}
-# else /* NOT_ISA_TARGET_32BIT */
-ARM_FUNC_START clzdi2
- do_push {r4, lr}
- cmp xxh, #0
- bne 1f
-# ifdef __ARMEB__
- mov r0, xxl
- bl __clzsi2
- add r0, r0, #32
- b 2f
-1:
- bl __clzsi2
-# else
- bl __clzsi2
- add r0, r0, #32
- b 2f
-1:
- mov r0, xxh
- bl __clzsi2
-# endif
-2:
- RETLDM r4
- FUNC_END clzdi2
-# endif /* NOT_ISA_TARGET_32BIT */
-
-#else /* defined (__ARM_FEATURE_CLZ) */
-
-ARM_FUNC_START clzdi2
- cmp xxh, #0
- do_it eq, et
- clzeq r0, xxl
- clzne r0, xxh
- addeq r0, r0, #32
- RET
- FUNC_END clzdi2
-#endif
+// int __clzdi2(long long)
+// Counts leading zero bits in $r1:$r0.
+// Returns the result in $r0.
+// Uses $r2 and possibly $r3 as scratch space.
+FUNC_START_SECTION clzdi2 .text.sorted.libgcc.clz2.clzdi2
+ CFI_START_FUNCTION
+
+ #if defined(__ARMEB__) && __ARMEB__
+ // Check if the upper word is zero.
+ cmp r0, #0
+
+ // The upper word is non-zero, so calculate __clzsi2(upper).
+ bne SYM(__clzsi2)
+
+ // The upper word is zero, so calculate 32 + __clzsi2(lower).
+ movs r2, #64
+ movs r0, r1
+ b SYM(__internal_clzsi2)
+
+ #else /* !__ARMEB__ */
+ // Assume all the bits in the argument are zero.
+ movs r2, #64
+
+ // Check if the upper word is zero.
+ cmp r1, #0
+
+ // The upper word is zero, so calculate 32 + __clzsi2(lower).
+ beq SYM(__internal_clzsi2)
+
+ // The upper word is non-zero, so set up __clzsi2(upper).
+ // Then fall through.
+ movs r0, r1
+
+ #endif /* !__ARMEB__ */
+
#endif /* L_clzdi2 */
+
+// The bitwise implementation of __clzdi2() tightly couples with __clzsi2(),
+// such that instructions must appear consecutively in the same memory
+// section for proper flow control. However, this construction inhibits
+// the ability to discard __clzdi2() when only using __clzsi2().
+// Therefore, this block configures __clzsi2() for compilation twice.
+// The first version is a minimal standalone implementation, and the second
+// version is the continuation of __clzdi2(). The standalone version must
+// be declared WEAK, so that the combined version can supersede it and
+// provide both symbols when required.
+// '_clzsi2' should appear before '_clzdi2' in LIB1ASMFUNCS.
+#if defined(L_clzsi2) || defined(L_clzdi2)
+
+#ifdef L_clzsi2
+// int __clzsi2(int)
+// Counts leading zero bits in $r0.
+// Returns the result in $r0.
+// Uses $r2 and possibly $r3 as scratch space.
+WEAK_START_SECTION clzsi2 .text.sorted.libgcc.clz2.clzsi2
+ CFI_START_FUNCTION
+
+#else /* L_clzdi2 */
+FUNC_ENTRY clzsi2
+
+#endif
+
+ // Assume all the bits in the argument are zero
+ movs r2, #32
+
+#ifdef L_clzsi2
+ WEAK_ENTRY internal_clzsi2
+#else /* L_clzdi2 */
+ FUNC_ENTRY internal_clzsi2
+#endif
+
+ // Size optimized: 22 bytes, 51 cycles
+ // Speed optimized: 50 bytes, 20 cycles
+
+ #if defined(__OPTIMIZE_SIZE__) && __OPTIMIZE_SIZE__
+
+ // Binary search starts at half the word width.
+ movs r3, #16
+
+ LLSYM(__clz_loop):
+ // Test the upper 'n' bits of the operand for ZERO.
+ movs r1, r0
+ lsrs r1, r3
+
+ // When the test fails, discard the lower bits of the register,
+ // and deduct the count of discarded bits from the result.
+ #ifdef __HAVE_FEATURE_IT
+ do_it ne, t
+ #else
+ beq LLSYM(__clz_skip)
+ #endif
+
+ IT(mov,ne) r0, r1
+ IT(sub,ne) r2, r3
+
+ LLSYM(__clz_skip):
+ // Decrease the shift distance for the next test.
+ lsrs r3, #1
+ bne LLSYM(__clz_loop)
+
+ #else /* __OPTIMIZE_SIZE__ */
+
+ // Unrolled binary search.
+ lsrs r1, r0, #16
+
+ #ifdef __HAVE_FEATURE_IT
+ do_it ne,t
+ #else
+ beq LLSYM(__clz8)
+ #endif
+
+ // Out of 32 bits, the first '1' is somewhere in the highest 16,
+ // so the lower 16 bits are no longer interesting.
+ IT(mov,ne) r0, r1
+ IT(sub,ne) r2, #16
+
+ LLSYM(__clz8):
+ lsrs r1, r0, #8
+
+ #ifdef __HAVE_FEATURE_IT
+ do_it ne,t
+ #else
+ beq LLSYM(__clz4)
+ #endif
+
+ // Out of 16 bits, the first '1' is somewhere in the highest 8,
+ // so the lower 8 bits are no longer interesting.
+ IT(mov,ne) r0, r1
+ IT(sub,ne) r2, #8
+
+ LLSYM(__clz4):
+ lsrs r1, r0, #4
+
+ #ifdef __HAVE_FEATURE_IT
+ do_it ne,t
+ #else
+ beq LLSYM(__clz2)
+ #endif
+
+ // Out of 8 bits, the first '1' is somewhere in the highest 4,
+ // so the lower 4 bits are no longer interesting.
+ IT(mov,ne) r0, r1
+ IT(sub,ne) r2, #4
+
+ LLSYM(__clz2):
+ // Load the remainder by index
+ adr r1, LLSYM(__clz_remainder)
+ ldrb r0, [r1, r0]
+
+ #endif /* !__OPTIMIZE_SIZE__ */
+
+ // Account for the remainder.
+ subs r0, r2, r0
+ RET
+
+ #if !defined(__OPTIMIZE_SIZE__) || !__OPTIMIZE_SIZE__
+ .align 2
+ LLSYM(__clz_remainder):
+ .byte 0,1,2,2,3,3,3,3,4,4,4,4,4,4,4,4
+ #endif
+
+ CFI_END_FUNCTION
+FUNC_END internal_clzsi2
+FUNC_END clzsi2
+
+#ifdef L_clzdi2
+FUNC_END clzdi2
+#endif
+
+#endif /* L_clzsi2 || L_clzdi2 */
+
+#endif /* !__ARM_FEATURE_CLZ */
+
diff --git a/libgcc/config/arm/t-elf b/libgcc/config/arm/t-elf
index 93ea1cd8f76..af779afa0a9 100644
--- a/libgcc/config/arm/t-elf
+++ b/libgcc/config/arm/t-elf
@@ -19,13 +19,18 @@ endif # !__symbian__
# assembly implementation here for double-precision values.
+# Group 0: WEAK overridable function objects.
+# See respective sources for rationale.
+LIB1ASMFUNCS += \
+ _clzsi2 \
+
+
# Group 1: Integer function objects.
LIB1ASMFUNCS += \
_ashldi3 \
_ashrdi3 \
_lshrdi3 \
_clzdi2 \
- _clzsi2 \
_ctzsi2 \
_dvmd_tls \
_divsi3 \
--
2.34.1
next prev parent reply other threads:[~2022-10-31 15:46 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 ` Daniel Engel [this message]
2022-10-31 15:45 ` [PATCH v7 10/34] Import 'ctz' functions from the CM0 library 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 ` [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=20221031154529.3627576-10-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).