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 29/34] Import integer-to-float conversion from the CM0 library
Date: Mon, 31 Oct 2022 08:45:24 -0700 [thread overview]
Message-ID: <20221031154529.3627576-30-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/bpabi-lib.h (__floatdisf, __floatundisf):
Remove obsolete RENAME_LIBRARY directives.
* config/arm/eabi/ffloat.S (__aeabi_i2f, __aeabi_l2f, __aeabi_ui2f,
__aeabi_ul2f): New file.
* config/arm/lib1funcs.S: #include eabi/ffloat.S (v6m only).
* config/arm/t-elf (LIB1ASMFUNCS): Added _arm_floatunsisf,
_arm_floatsisf, and _internal_floatundisf.
Moved _arm_floatundisf to the weak function group
---
libgcc/config/arm/bpabi-lib.h | 6 -
libgcc/config/arm/eabi/ffloat.S | 247 ++++++++++++++++++++++++++++++++
libgcc/config/arm/lib1funcs.S | 1 +
libgcc/config/arm/t-elf | 5 +-
4 files changed, 252 insertions(+), 7 deletions(-)
create mode 100644 libgcc/config/arm/eabi/ffloat.S
diff --git a/libgcc/config/arm/bpabi-lib.h b/libgcc/config/arm/bpabi-lib.h
index 26ad5ffbe8b..7dd78d5668f 100644
--- a/libgcc/config/arm/bpabi-lib.h
+++ b/libgcc/config/arm/bpabi-lib.h
@@ -56,9 +56,6 @@
#ifdef L_floatdidf
#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (floatdidf, l2d)
#endif
-#ifdef L_floatdisf
-#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (floatdisf, l2f)
-#endif
/* These renames are needed on ARMv6M. Other targets get them from
assembly routines. */
@@ -71,9 +68,6 @@
#ifdef L_floatundidf
#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (floatundidf, ul2d)
#endif
-#ifdef L_floatundisf
-#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (floatundisf, ul2f)
-#endif
/* For ARM bpabi, we only want to use a "__gnu_" prefix for the fixed-point
helper functions - not everything in libgcc - in the interests of
diff --git a/libgcc/config/arm/eabi/ffloat.S b/libgcc/config/arm/eabi/ffloat.S
new file mode 100644
index 00000000000..c8bc55a24b6
--- /dev/null
+++ b/libgcc/config/arm/eabi/ffloat.S
@@ -0,0 +1,247 @@
+/* ffixed.S: Thumb-1 optimized integer-to-float conversion
+
+ 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_arm_floatsisf
+
+// float __aeabi_i2f(int)
+// Converts a signed integer in $r0 to float.
+
+// On little-endian cores (including all Cortex-M), __floatsisf() can be
+// implemented as below in 5 instructions. However, it can also be
+// implemented by prefixing a single instruction to __floatdisf().
+// A memory savings of 4 instructions at a cost of only 2 execution cycles
+// seems reasonable enough. Plus, the trade-off only happens in programs
+// that require both __floatsisf() and __floatdisf(). Programs only using
+// __floatsisf() always get the smallest version.
+// When the combined version will be provided, this standalone version
+// must be declared WEAK, so that the combined version can supersede it.
+// '_arm_floatsisf' should appear before '_arm_floatdisf' in LIB1ASMFUNCS.
+// Same parent section as __ul2f() to keep tail call branch within range.
+#if defined(__OPTIMIZE_SIZE__) && __OPTIMIZE_SIZE__
+WEAK_START_SECTION aeabi_i2f .text.sorted.libgcc.fpcore.p.floatsisf
+WEAK_ALIAS floatsisf aeabi_i2f
+ CFI_START_FUNCTION
+
+#else /* !__OPTIMIZE_SIZE__ */
+FUNC_START_SECTION aeabi_i2f .text.sorted.libgcc.fpcore.p.floatsisf
+FUNC_ALIAS floatsisf aeabi_i2f
+ CFI_START_FUNCTION
+
+#endif /* !__OPTIMIZE_SIZE__ */
+
+ // Save the sign.
+ asrs r3, r0, #31
+
+ // Absolute value of the input.
+ eors r0, r3
+ subs r0, r3
+
+ // Sign extension to long long unsigned.
+ eors r1, r1
+ b SYM(__internal_floatundisf_noswap)
+
+ CFI_END_FUNCTION
+FUNC_END floatsisf
+FUNC_END aeabi_i2f
+
+#endif /* L_arm_floatsisf */
+
+
+#ifdef L_arm_floatdisf
+
+// float __aeabi_l2f(long long)
+// Converts a signed 64-bit integer in $r1:$r0 to a float in $r0.
+// See build comments for __floatsisf() above.
+// Same parent section as __ul2f() to keep tail call branch within range.
+#if defined(__OPTIMIZE_SIZE__) && __OPTIMIZE_SIZE__
+FUNC_START_SECTION aeabi_i2f .text.sorted.libgcc.fpcore.p.floatdisf
+FUNC_ALIAS floatsisf aeabi_i2f
+ CFI_START_FUNCTION
+
+ #if defined(__ARMEB__) && __ARMEB__
+ // __floatdisf() expects a big-endian lower word in $r1.
+ movs xxl, r0
+ #endif
+
+ // Sign extension to long long signed.
+ asrs xxh, xxl, #31
+
+ FUNC_ENTRY aeabi_l2f
+ FUNC_ALIAS floatdisf aeabi_l2f
+
+#else /* !__OPTIMIZE_SIZE__ */
+FUNC_START_SECTION aeabi_l2f .text.sorted.libgcc.fpcore.p.floatdisf
+FUNC_ALIAS floatdisf aeabi_l2f
+ CFI_START_FUNCTION
+
+#endif
+
+ // Save the sign.
+ asrs r3, xxh, #31
+
+ // Absolute value of the input.
+ // Could this be arranged in big-endian mode so that this block also
+ // swapped the input words? Maybe. But, since neither 'eors' nor
+ // 'sbcs' allow a third destination register, it seems unlikely to
+ // save more than one cycle. Also, the size of __floatdisf() and
+ // __floatundisf() together would increase by two instructions.
+ eors xxl, r3
+ eors xxh, r3
+ subs xxl, r3
+ sbcs xxh, r3
+
+ b SYM(__internal_floatundisf)
+
+ CFI_END_FUNCTION
+FUNC_END floatdisf
+FUNC_END aeabi_l2f
+
+#if defined(__OPTIMIZE_SIZE__) && __OPTIMIZE_SIZE__
+FUNC_END floatsisf
+FUNC_END aeabi_i2f
+#endif
+
+#endif /* L_arm_floatsisf || L_arm_floatdisf */
+
+
+#ifdef L_arm_floatunsisf
+
+// float __aeabi_ui2f(unsigned)
+// Converts an unsigned integer in $r0 to float.
+FUNC_START_SECTION aeabi_ui2f .text.sorted.libgcc.fpcore.q.floatunsisf
+FUNC_ALIAS floatunsisf aeabi_ui2f
+ CFI_START_FUNCTION
+
+ #if defined(__ARMEB__) && __ARMEB__
+ // In big-endian mode, function flow breaks down. __floatundisf()
+ // wants to swap word order, but __floatunsisf() does not. The
+ // The choice is between leaving these arguments un-swapped and
+ // branching, or canceling out the word swap in advance.
+ // The branching version would require one extra instruction to
+ // clear the sign ($r3) because of __floatdisf() dependencies.
+ // While the branching version is technically one cycle faster
+ // on the Cortex-M0 pipeline, branchless just feels better.
+
+ // Thus, __floatundisf() expects a big-endian lower word in $r1.
+ movs xxl, r0
+ #endif
+
+ // Extend to unsigned long long and fall through.
+ eors xxh, xxh
+
+#endif /* L_arm_floatunsisf */
+
+
+// The execution of __floatunsisf() flows directly into __floatundisf(), such
+// that instructions must appear consecutively in the same memory section
+// for proper flow control. However, this construction inhibits the ability
+// to discard __floatunsisf() when only using __floatundisf().
+// Additionally, both __floatsisf() and __floatdisf() expect to tail call
+// __internal_floatundisf() with a sign argument. The __internal_floatundisf()
+// symbol itself is unambiguous, but there is a remote risk that the linker
+// will prefer some other symbol in place of __floatsisf() or __floatdisf().
+// As a workaround, this block configures __internal_floatundisf() three times.
+// The first version provides __internal_floatundisf() as a WEAK standalone
+// symbol. The second provides __floatundisf() and __internal_floatundisf(),
+// still as weak symbols. The third provides __floatunsisf() normally, but
+// __floatundisf() remains weak in case the linker prefers another version.
+// '_internal_floatundisf', '_arm_floatundisf', and '_arm_floatunsisf' should
+// appear in the given order in LIB1ASMFUNCS.
+#if defined(L_arm_floatunsisf) || defined(L_arm_floatundisf) || \
+ defined(L_internal_floatundisf)
+
+#define UL2F_SECTION .text.sorted.libgcc.fpcore.q.floatundisf
+
+#if defined(L_arm_floatundisf)
+// float __aeabi_ul2f(unsigned long long)
+// Converts an unsigned 64-bit integer in $r1:$r0 to a float in $r0.
+WEAK_START_SECTION aeabi_ul2f UL2F_SECTION
+WEAK_ALIAS floatundisf aeabi_ul2f
+ CFI_START_FUNCTION
+#elif defined(L_arm_floatunsisf)
+FUNC_ENTRY aeabi_ul2f
+FUNC_ALIAS floatundisf aeabi_ul2f
+#endif
+
+#if defined(L_arm_floatundisf) || defined(L_arm_floatunsisf)
+ // Sign is always positive.
+ eors r3, r3
+#endif
+
+#if defined(L_arm_floatunsisf)
+ // float internal_floatundisf(unsigned long long, int)
+ // Internal function expects the sign of the result in $r3[0].
+ FUNC_ENTRY internal_floatundisf
+
+#elif defined(L_arm_floatundisf)
+ WEAK_ENTRY internal_floatundisf
+
+#else /* L_internal_floatundisf */
+ WEAK_START_SECTION internal_floatundisf UL2F_SECTION
+ CFI_START_FUNCTION
+
+#endif
+
+ #if defined(__ARMEB__) && __ARMEB__
+ // Swap word order for register compatibility with __fp_assemble().
+ // Could this be optimized by re-defining __fp_assemble()? Maybe.
+ // But the ramifications of dynamic register assignment on all
+ // the other callers of __fp_assemble() would be enormous.
+ eors r0, r1
+ eors r1, r0
+ eors r0, r1
+ #endif
+
+#ifdef L_arm_floatunsisf
+ FUNC_ENTRY internal_floatundisf_noswap
+#else /* L_arm_floatundisf || L_internal_floatundisf */
+ WEAK_ENTRY internal_floatundisf_noswap
+#endif
+ // Default exponent, relative to bit[30] of $r1.
+ movs r2, #(127 - 1 + 63)
+
+ // Format the sign.
+ lsls r3, #31
+ mov ip, r3
+
+ push { rT, lr }
+ b SYM(__fp_assemble)
+
+ CFI_END_FUNCTION
+FUNC_END internal_floatundisf_noswap
+FUNC_END internal_floatundisf
+
+#if defined(L_arm_floatundisf) || defined(L_arm_floatunsisf)
+FUNC_END floatundisf
+FUNC_END aeabi_ul2f
+#endif
+
+#if defined(L_arm_floatunsisf)
+FUNC_END floatunsisf
+FUNC_END aeabi_ui2f
+#endif
+
+#endif /* L_arm_floatunsisf || L_arm_floatundisf */
+
diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S
index bd146aedc14..67bff9777fd 100644
--- a/libgcc/config/arm/lib1funcs.S
+++ b/libgcc/config/arm/lib1funcs.S
@@ -2017,6 +2017,7 @@ LSYM(Lchange_\register):
#include "eabi/futil.S"
#include "eabi/fmul.S"
#include "eabi/fdiv.S"
+#include "eabi/ffloat.S"
#endif /* NOT_ISA_TARGET_32BIT */
#include "eabi/lcmp.S"
#endif /* !__symbian__ */
diff --git a/libgcc/config/arm/t-elf b/libgcc/config/arm/t-elf
index 1812a1e1a99..645d20f5f1c 100644
--- a/libgcc/config/arm/t-elf
+++ b/libgcc/config/arm/t-elf
@@ -26,14 +26,17 @@ LIB1ASMFUNCS += \
_ctzsi2 \
_paritysi2 \
_popcountsi2 \
+ _arm_floatundisf \
_arm_mulsf3 \
ifeq (__ARM_ARCH_ISA_THUMB 1,$(ARM_ISA)$(THUMB1_ISA))
# Group 0B: WEAK overridable function objects built for v6m only.
LIB1ASMFUNCS += \
_internal_cmpsf2 \
+ _internal_floatundisf \
_muldi3 \
_arm_addsf3 \
+ _arm_floatsisf \
endif
@@ -78,7 +81,6 @@ LIB1ASMFUNCS += \
_arm_fixsfsi \
_arm_fixunssfsi \
_arm_floatdisf \
- _arm_floatundisf \
_arm_muldivsf3 \
_arm_negsf2 \
_arm_unordsf2 \
@@ -99,6 +101,7 @@ LIB1ASMFUNCS += \
_arm_gesf2 \
_arm_frsubsf3 \
_arm_divsf3 \
+ _arm_floatunsisf \
_fp_exceptionf \
_fp_checknanf \
_fp_assemblef \
--
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 ` [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 ` Daniel Engel [this message]
2022-10-31 15:45 ` [PATCH v7 30/34] Import float-to-integer conversion " 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=20221031154529.3627576-30-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).