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 12/34] Import 'clrsb' functions from the CM0 library
Date: Mon, 31 Oct 2022 08:45:07 -0700	[thread overview]
Message-ID: <20221031154529.3627576-13-gnu@danielengel.com> (raw)
In-Reply-To: <20221031154529.3627576-1-gnu@danielengel.com>

This implementation provides an efficient tail call to __clzsi2(), making the
functions rather smaller and faster than the C versions.

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

	* config/arm/bits/clz2.S (__clrsbsi2, __clrsbdi2):
	Added new functions.
	* config/arm/t-elf (LIB1ASMFUNCS):
	Added new function objects _clrsbsi2 and _clrsbdi2).
---
 libgcc/config/arm/clz2.S | 108 ++++++++++++++++++++++++++++++++++++++-
 libgcc/config/arm/t-elf  |   2 +
 2 files changed, 108 insertions(+), 2 deletions(-)

diff --git a/libgcc/config/arm/clz2.S b/libgcc/config/arm/clz2.S
index ed04698fef4..3d40811278b 100644
--- a/libgcc/config/arm/clz2.S
+++ b/libgcc/config/arm/clz2.S
@@ -1,4 +1,4 @@
-/* clz2.S: Cortex M0 optimized 'clz' functions
+/* clz2.S: ARM optimized 'clz' and related functions
 
    Copyright (C) 2018-2022 Free Software Foundation, Inc.
    Contributed by Daniel Engel (gnu@danielengel.com)
@@ -23,7 +23,7 @@
    <http://www.gnu.org/licenses/>.  */
 
 
-#if defined(__ARM_FEATURE_CLZ) && __ARM_FEATURE_CLZ
+#ifdef __ARM_FEATURE_CLZ
 
 #ifdef L_clzdi2
 
@@ -242,3 +242,107 @@ FUNC_END clzdi2
 
 #endif /* !__ARM_FEATURE_CLZ */
 
+
+#ifdef L_clrsbdi2
+
+// int __clrsbdi2(int)
+// Counts the number of "redundant sign bits" in $r1:$r0.
+// Returns the result in $r0.
+// Uses $r2 and $r3 as scratch space.
+FUNC_START_SECTION clrsbdi2 .text.sorted.libgcc.clz2.clrsbdi2
+    CFI_START_FUNCTION
+
+  #if defined(__ARM_FEATURE_CLZ) && __ARM_FEATURE_CLZ
+        // Invert negative signs to keep counting zeros.
+        asrs    r3,     xxh,    #31
+        eors    xxl,    r3
+        eors    xxh,    r3
+
+        // Same as __clzdi2(), except that the 'C' flag is pre-calculated.
+        // Also, the trailing 'subs', since the last bit is not redundant.
+        do_it   eq,     et
+        clzeq   r0,     xxl
+        clzne   r0,     xxh
+        addeq   r0,     #32
+        subs    r0,     #1
+        RET
+
+  #else  /* !__ARM_FEATURE_CLZ */
+        // Result if all the bits in the argument are zero.
+        // Set it here to keep the flags clean after 'eors' below.
+        movs    r2,     #31
+
+        // Invert negative signs to keep counting zeros.
+        asrs    r3,     xxh,    #31
+        eors    xxh,    r3
+
+    #if defined(__ARMEB__) && __ARMEB__
+        // If the upper word is non-zero, return '__clzsi2(upper) - 1'.
+        bne     SYM(__internal_clzsi2)
+
+        // The upper word is zero, prepare the lower word.
+        movs    r0,     r1
+        eors    r0,     r3
+
+    #else /* !__ARMEB__ */
+        // Save the lower word temporarily.
+        // This somewhat awkward construction adds one cycle when the
+        //  branch is not taken, but prevents a double-branch.
+        eors    r3,     r0
+
+        // If the upper word is non-zero, return '__clzsi2(upper) - 1'.
+        movs    r0,     r1
+        bne    SYM(__internal_clzsi2)
+
+        // Restore the lower word.
+        movs    r0,     r3
+
+    #endif /* !__ARMEB__ */
+
+        // The upper word is zero, return '31 + __clzsi2(lower)'.
+        adds    r2,     #32
+        b       SYM(__internal_clzsi2)
+
+  #endif /* !__ARM_FEATURE_CLZ */
+
+    CFI_END_FUNCTION
+FUNC_END clrsbdi2
+
+#endif /* L_clrsbdi2 */
+
+
+#ifdef L_clrsbsi2
+
+// int __clrsbsi2(int)
+// Counts the number of "redundant sign bits" in $r0.
+// Returns the result in $r0.
+// Uses $r2 and possibly $r3 as scratch space.
+FUNC_START_SECTION clrsbsi2 .text.sorted.libgcc.clz2.clrsbsi2
+    CFI_START_FUNCTION
+
+        // Invert negative signs to keep counting zeros.
+        asrs    r2,     r0,    #31
+        eors    r0,     r2
+
+      #if defined(__ARM_FEATURE_CLZ) && __ARM_FEATURE_CLZ
+        // Count.
+        clz     r0,     r0
+
+        // The result for a positive value will always be >= 1.
+        // By definition, the last bit is not redundant.
+        subs    r0,     #1
+        RET
+
+      #else /* !__ARM_FEATURE_CLZ */
+        // Result if all the bits in the argument are zero.
+        // By definition, the last bit is not redundant.
+        movs    r2,     #31
+        b       SYM(__internal_clzsi2)
+
+      #endif  /* !__ARM_FEATURE_CLZ */
+
+    CFI_END_FUNCTION
+FUNC_END clrsbsi2
+
+#endif /* L_clrsbsi2 */
+
diff --git a/libgcc/config/arm/t-elf b/libgcc/config/arm/t-elf
index 33b83ac4adf..89071cebe45 100644
--- a/libgcc/config/arm/t-elf
+++ b/libgcc/config/arm/t-elf
@@ -31,6 +31,8 @@ LIB1ASMFUNCS += \
 	_ashldi3 \
 	_ashrdi3 \
 	_lshrdi3 \
+	_clrsbsi2 \
+	_clrsbdi2 \
 	_clzdi2 \
 	_ctzdi2 \
 	_dvmd_tls \
-- 
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 ` Daniel Engel [this message]
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=20221031154529.3627576-13-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).