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 17/34] Import 64-bit comparison from CM0 library
Date: Mon, 31 Oct 2022 08:45:12 -0700	[thread overview]
Message-ID: <20221031154529.3627576-18-gnu@danielengel.com> (raw)
In-Reply-To: <20221031154529.3627576-1-gnu@danielengel.com>

These are 2-5 instructions smaller and just as fast.  Branches are
minimized, which will allow easier adaptation to Thumb-2/ARM mode.

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

	* config/arm/eabi/lcmp.S (__aeabi_lcmp, __aeabi_ulcmp): Replaced;
	add macro configuration to build __cmpdi2() and __ucmpdi2().
	* config/arm/t-elf (LIB1ASMFUNCS): Added _cmpdi2 and _ucmpdi2.
---
 libgcc/config/arm/eabi/lcmp.S | 151 +++++++++++++++++++++++++---------
 libgcc/config/arm/t-elf       |   2 +
 2 files changed, 112 insertions(+), 41 deletions(-)

diff --git a/libgcc/config/arm/eabi/lcmp.S b/libgcc/config/arm/eabi/lcmp.S
index 336db1d398c..99c7970ecba 100644
--- a/libgcc/config/arm/eabi/lcmp.S
+++ b/libgcc/config/arm/eabi/lcmp.S
@@ -1,8 +1,7 @@
-/* Miscellaneous BPABI functions.  Thumb-1 implementation, suitable for ARMv4T,
-   ARMv6-M and ARMv8-M Baseline like ISA variants.
+/* lcmp.S: Thumb-1 optimized 64-bit integer comparison
 
-   Copyright (C) 2006-2020 Free Software Foundation, Inc.
-   Contributed by CodeSourcery.
+   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
@@ -24,50 +23,120 @@
    <http://www.gnu.org/licenses/>.  */
 
 
+#if defined(L_aeabi_lcmp) || defined(L_cmpdi2)
+
 #ifdef L_aeabi_lcmp
+  #define LCMP_NAME aeabi_lcmp
+  #define LCMP_SECTION .text.sorted.libgcc.lcmp
+#else
+  #define LCMP_NAME cmpdi2
+  #define LCMP_SECTION .text.sorted.libgcc.cmpdi2
+#endif
+
+// int __aeabi_lcmp(long long, long long)
+// int __cmpdi2(long long, long long)
+// Compares the 64 bit signed values in $r1:$r0 and $r3:$r2.
+// lcmp() returns $r0 = { -1, 0, +1 } for orderings { <, ==, > } respectively.
+// cmpdi2() returns $r0 = { 0, 1, 2 } for orderings { <, ==, > } respectively.
+// Object file duplication assumes typical programs follow one runtime ABI.
+FUNC_START_SECTION LCMP_NAME LCMP_SECTION
+    CFI_START_FUNCTION
+
+        // Calculate the difference $r1:$r0 - $r3:$r2.
+        subs    xxl,    yyl
+        sbcs    xxh,    yyh
+
+        // With $r2 free, create a known offset value without affecting
+        //  the N or Z flags.
+        // BUG? The originally unified instruction for v6m was 'mov r2, r3'.
+        //  However, this resulted in a compile error with -mthumb:
+        //    "MOV Rd, Rs with two low registers not permitted".
+        // Since unified syntax deprecates the "cpy" instruction, shouldn't
+        //  there be a backwards-compatible tranlation available?
+        cpy     r2,     r3
+
+        // Evaluate the comparison result.
+        blt     LLSYM(__lcmp_lt)
+
+        // The reference offset ($r2 - $r3) will be +2 iff the first
+        //  argument is larger, otherwise the offset value remains 0.
+        adds    r2,     #2
+
+        // Check for zero (equality in 64 bits).
+        // It doesn't matter which register was originally "hi".
+        orrs    r0,    r1
+
+        // The result is already 0 on equality.
+        beq     LLSYM(__lcmp_return)
+
+    LLSYM(__lcmp_lt):
+        // Create +1 or -1 from the offset value defined earlier.
+        adds    r3,     #1
+        subs    r0,     r2,     r3
+
+    LLSYM(__lcmp_return):
+      #ifdef L_cmpdi2
+        // Offset to the correct output specification.
+        adds    r0,     #1
+      #endif
 
-FUNC_START aeabi_lcmp
-        cmp     xxh, yyh
-        beq     1f
-        bgt     2f
-        movs    r0, #1
-        negs    r0, r0
-        RET
-2:
-        movs    r0, #1
-        RET
-1:
-        subs    r0, xxl, yyl
-        beq     1f
-        bhi     2f
-        movs    r0, #1
-        negs    r0, r0
-        RET
-2:
-        movs    r0, #1
-1:
         RET
-        FUNC_END aeabi_lcmp
 
-#endif /* L_aeabi_lcmp */
+    CFI_END_FUNCTION
+FUNC_END LCMP_NAME
+
+#endif /* L_aeabi_lcmp || L_cmpdi2 */
+
+
+#if defined(L_aeabi_ulcmp) || defined(L_ucmpdi2)
 
 #ifdef L_aeabi_ulcmp
+  #define ULCMP_NAME aeabi_ulcmp
+  #define ULCMP_SECTION .text.sorted.libgcc.ulcmp
+#else
+  #define ULCMP_NAME ucmpdi2
+  #define ULCMP_SECTION .text.sorted.libgcc.ucmpdi2
+#endif
+
+// int __aeabi_ulcmp(unsigned long long, unsigned long long)
+// int __ucmpdi2(unsigned long long, unsigned long long)
+// Compares the 64 bit unsigned values in $r1:$r0 and $r3:$r2.
+// ulcmp() returns $r0 = { -1, 0, +1 } for orderings { <, ==, > } respectively.
+// ucmpdi2() returns $r0 = { 0, 1, 2 } for orderings { <, ==, > } respectively.
+// Object file duplication assumes typical programs follow one runtime ABI.
+FUNC_START_SECTION ULCMP_NAME ULCMP_SECTION
+    CFI_START_FUNCTION
+
+        // Calculate the 'C' flag.
+        subs    xxl,    yyl
+        sbcs    xxh,    yyh
+
+        // Capture the carry flg.
+        // $r2 will contain -1 if the first value is smaller,
+        //  0 if the first value is larger or equal.
+        sbcs    r2,     r2
+
+        // Check for zero (equality in 64 bits).
+        // It doesn't matter which register was originally "hi".
+        orrs    r0,     r1
+
+        // The result is already 0 on equality.
+        beq     LLSYM(__ulcmp_return)
+
+        // Assume +1.  If -1 is correct, $r2 will override.
+        movs    r0,     #1
+        orrs    r0,     r2
+
+    LLSYM(__ulcmp_return):
+      #ifdef L_ucmpdi2
+        // Offset to the correct output specification.
+        adds    r0,     #1
+      #endif
 
-FUNC_START aeabi_ulcmp
-        cmp     xxh, yyh
-        bne     1f
-        subs    r0, xxl, yyl
-        beq     2f
-1:
-        bcs     1f
-        movs    r0, #1
-        negs    r0, r0
-        RET
-1:
-        movs    r0, #1
-2:
         RET
-        FUNC_END aeabi_ulcmp
 
-#endif /* L_aeabi_ulcmp */
+    CFI_END_FUNCTION
+FUNC_END ULCMP_NAME
+
+#endif /* L_aeabi_ulcmp || L_ucmpdi2 */
 
diff --git a/libgcc/config/arm/t-elf b/libgcc/config/arm/t-elf
index 2e3f04aa2f0..83325410097 100644
--- a/libgcc/config/arm/t-elf
+++ b/libgcc/config/arm/t-elf
@@ -41,6 +41,8 @@ LIB1ASMFUNCS += \
 	_ffsdi2 \
 	_paritydi2 \
 	_popcountdi2 \
+	_cmpdi2 \
+	_ucmpdi2 \
 	_dvmd_tls \
 	_divsi3 \
 	_modsi3 \
-- 
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 ` [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 ` Daniel Engel [this message]
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=20221031154529.3627576-18-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).