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 27/34] Import float multiplication from the CM0 library
Date: Mon, 31 Oct 2022 08:45:22 -0700 [thread overview]
Message-ID: <20221031154529.3627576-28-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/fmul.S (__mulsf3): New file.
* config/arm/lib1funcs.S: #include eabi/fmul.S (v6m only).
* config/arm/t-elf (LIB1ASMFUNCS): Moved _mulsf3 to global scope
(this object was previously blocked on v6m builds).
---
libgcc/config/arm/eabi/fmul.S | 215 ++++++++++++++++++++++++++++++++++
libgcc/config/arm/lib1funcs.S | 1 +
libgcc/config/arm/t-elf | 3 +-
3 files changed, 218 insertions(+), 1 deletion(-)
create mode 100644 libgcc/config/arm/eabi/fmul.S
diff --git a/libgcc/config/arm/eabi/fmul.S b/libgcc/config/arm/eabi/fmul.S
new file mode 100644
index 00000000000..4ebd5a66f47
--- /dev/null
+++ b/libgcc/config/arm/eabi/fmul.S
@@ -0,0 +1,215 @@
+/* fmul.S: Thumb-1 optimized 32-bit float 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_arm_mulsf3
+
+// float __aeabi_fmul(float, float)
+// Returns $r0 after multiplication by $r1.
+// Subsection ordering within fpcore keeps conditional branches within range.
+FUNC_START_SECTION aeabi_fmul .text.sorted.libgcc.fpcore.m.fmul
+FUNC_ALIAS mulsf3 aeabi_fmul
+ CFI_START_FUNCTION
+
+ // Standard registers, compatible with exception handling.
+ push { rT, lr }
+ .cfi_remember_state
+ .cfi_remember_state
+ .cfi_adjust_cfa_offset 8
+ .cfi_rel_offset rT, 0
+ .cfi_rel_offset lr, 4
+
+ // Save the sign of the result.
+ movs rT, r1
+ eors rT, r0
+ lsrs rT, #31
+ lsls rT, #31
+ mov ip, rT
+
+ // Set up INF for comparison.
+ movs rT, #255
+ lsls rT, #24
+
+ // Check for multiplication by zero.
+ lsls r2, r0, #1
+ beq LLSYM(__fmul_zero1)
+
+ lsls r3, r1, #1
+ beq LLSYM(__fmul_zero2)
+
+ // Check for INF/NAN.
+ cmp r3, rT
+ bhs LLSYM(__fmul_special2)
+
+ cmp r2, rT
+ bhs LLSYM(__fmul_special1)
+
+ // Because neither operand is INF/NAN, the result will be finite.
+ // It is now safe to modify the original operand registers.
+ lsls r0, #9
+
+ // Isolate the first exponent. When normal, add back the implicit '1'.
+ // The result is always aligned with the MSB in bit [31].
+ // Subnormal mantissas remain effectively multiplied by 2x relative to
+ // normals, but this works because the weight of a subnormal is -126.
+ lsrs r2, #24
+ beq LLSYM(__fmul_normalize2)
+ adds r0, #1
+ rors r0, r0
+
+ LLSYM(__fmul_normalize2):
+ // IMPORTANT: exp10i() jumps in here!
+ // Repeat for the mantissa of the second operand.
+ // Short-circuit when the mantissa is 1.0, as the
+ // first mantissa is already prepared in $r0
+ lsls r1, #9
+
+ // When normal, add back the implicit '1'.
+ lsrs r3, #24
+ beq LLSYM(__fmul_go)
+ adds r1, #1
+ rors r1, r1
+
+ LLSYM(__fmul_go):
+ // Calculate the final exponent, relative to bit [30].
+ adds rT, r2, r3
+ subs rT, #127
+
+ #if !defined(__OPTIMIZE_SIZE__) || !__OPTIMIZE_SIZE__
+ // Short-circuit on multiplication by powers of 2.
+ lsls r3, r0, #1
+ beq LLSYM(__fmul_simple1)
+
+ lsls r3, r1, #1
+ beq LLSYM(__fmul_simple2)
+ #endif
+
+ // Save $ip across the call.
+ // (Alternatively, could push/pop a separate register,
+ // but the four instructions here are equivally fast)
+ // without imposing on the stack.
+ add rT, ip
+
+ // 32x32 unsigned multiplication, 64 bit result.
+ bl SYM(__umulsidi3) __PLT__
+
+ // Separate the saved exponent and sign.
+ sxth r2, rT
+ subs rT, r2
+ mov ip, rT
+
+ b SYM(__fp_assemble)
+
+ #if !defined(__OPTIMIZE_SIZE__) || !__OPTIMIZE_SIZE__
+ LLSYM(__fmul_simple2):
+ // Move the high bits of the result to $r1.
+ movs r1, r0
+
+ LLSYM(__fmul_simple1):
+ // Clear the remainder.
+ eors r0, r0
+
+ // Adjust mantissa to match the exponent, relative to bit[30].
+ subs r2, rT, #1
+ b SYM(__fp_assemble)
+ #endif
+
+ LLSYM(__fmul_zero1):
+ // $r0 was equal to 0, set up to check $r1 for INF/NAN.
+ lsls r2, r1, #1
+
+ LLSYM(__fmul_zero2):
+ #if defined(EXCEPTION_CODES) && EXCEPTION_CODES
+ movs r3, #(INFINITY_TIMES_ZERO)
+ #endif
+
+ // Check the non-zero operand for INF/NAN.
+ // If NAN, it should be returned.
+ // If INF, the result should be NAN.
+ // Otherwise, the result will be +/-0.
+ cmp r2, rT
+ beq SYM(__fp_exception)
+
+ // If the second operand is finite, the result is 0.
+ blo SYM(__fp_zero)
+
+ #if defined(STRICT_NANS) && STRICT_NANS
+ // Restore values that got mixed in zero testing, then go back
+ // to sort out which one is the NAN.
+ lsls r3, r1, #1
+ lsls r2, r0, #1
+ #elif defined(TRAP_NANS) && TRAP_NANS
+ // Return NAN with the sign bit cleared.
+ lsrs r0, r2, #1
+ b SYM(__fp_check_nan)
+ #else
+ lsrs r0, r2, #1
+ // Return NAN with the sign bit cleared.
+ pop { rT, pc }
+ .cfi_restore_state
+ #endif
+
+ LLSYM(__fmul_special2):
+ // $r1 is INF/NAN. In case of INF, check $r0 for NAN.
+ cmp r2, rT
+
+ #if defined(TRAP_NANS) && TRAP_NANS
+ // Force swap if $r0 is not NAN.
+ bls LLSYM(__fmul_swap)
+
+ // $r0 is NAN, keep if $r1 is INF
+ cmp r3, rT
+ beq LLSYM(__fmul_special1)
+
+ // Both are NAN, keep the smaller value (more likely to signal).
+ cmp r2, r3
+ #endif
+
+ // Prefer the NAN already in $r0.
+ // (If TRAP_NANS, this is the smaller NAN).
+ bhi LLSYM(__fmul_special1)
+
+ LLSYM(__fmul_swap):
+ movs r0, r1
+
+ LLSYM(__fmul_special1):
+ // $r0 is either INF or NAN. $r1 has already been examined.
+ // Flags are already set correctly.
+ lsls r2, r0, #1
+ cmp r2, rT
+ beq SYM(__fp_infinity)
+
+ #if defined(TRAP_NANS) && TRAP_NANS
+ b SYM(__fp_check_nan)
+ #else
+ pop { rT, pc }
+ .cfi_restore_state
+ #endif
+
+ CFI_END_FUNCTION
+FUNC_END mulsf3
+FUNC_END aeabi_fmul
+
+#endif /* L_arm_mulsf3 */
+
diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S
index bfe3397d892..92245353442 100644
--- a/libgcc/config/arm/lib1funcs.S
+++ b/libgcc/config/arm/lib1funcs.S
@@ -2015,6 +2015,7 @@ LSYM(Lchange_\register):
#include "eabi/fneg.S"
#include "eabi/fadd.S"
#include "eabi/futil.S"
+#include "eabi/fmul.S"
#endif /* NOT_ISA_TARGET_32BIT */
#include "eabi/lcmp.S"
#endif /* !__symbian__ */
diff --git a/libgcc/config/arm/t-elf b/libgcc/config/arm/t-elf
index c57d9ef50ac..682f273a1d2 100644
--- a/libgcc/config/arm/t-elf
+++ b/libgcc/config/arm/t-elf
@@ -10,7 +10,7 @@ THUMB1_ISA:=$(findstring __ARM_ARCH_ISA_THUMB 1,$(shell $(gcc_compile_bare) -dM
# inclusion create when only multiplication is used, thus avoiding pulling in
# useless division code.
ifneq (__ARM_ARCH_ISA_THUMB 1,$(ARM_ISA)$(THUMB1_ISA))
-LIB1ASMFUNCS += _arm_muldf3 _arm_mulsf3
+LIB1ASMFUNCS += _arm_muldf3
endif
endif # !__symbian__
@@ -26,6 +26,7 @@ LIB1ASMFUNCS += \
_ctzsi2 \
_paritysi2 \
_popcountsi2 \
+ _arm_mulsf3 \
ifeq (__ARM_ARCH_ISA_THUMB 1,$(ARM_ISA)$(THUMB1_ISA))
# Group 0B: WEAK overridable function objects built for v6m only.
--
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 ` Daniel Engel [this message]
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=20221031154529.3627576-28-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).