diff mbox series

[v6,14/34] Import 'parity' functions from the CM0 library

Message ID 20211227190530.3136549-15-gnu@danielengel.com
State New
Headers show
Series libgcc: Thumb-1 Floating-Point Assembly for Cortex M0 | expand

Commit Message

Daniel Engel Dec. 27, 2021, 7:05 p.m. UTC
The functional overlap between the single- and double-word functions makes
functions makes this implementation about half the size of the C functions
if both functions are linked in the same application.

gcc/libgcc/ChangeLog:
2021-01-13 Daniel Engel <gnu@danielengel.com>

	* config/arm/parity.S: New file for __paritysi2/di2().
	* config/arm/lib1funcs.S: #include bit/parity.S
	* config/arm/t-elf (LIB1ASMFUNCS): Added _paritysi2/di2.
---
 libgcc/config/arm/lib1funcs.S |   1 +
 libgcc/config/arm/parity.S    | 120 ++++++++++++++++++++++++++++++++++
 libgcc/config/arm/t-elf       |   2 +
 3 files changed, 123 insertions(+)
 create mode 100644 libgcc/config/arm/parity.S
diff mbox series

Patch

diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S
index 7ac50230725..600ea2dfdc9 100644
--- a/libgcc/config/arm/lib1funcs.S
+++ b/libgcc/config/arm/lib1funcs.S
@@ -1704,6 +1704,7 @@  LSYM(Lover12):
 
 #include "clz2.S"
 #include "ctz2.S"
+#include "parity.S"
 
 /* ------------------------------------------------------------------------ */
 /* These next two sections are here despite the fact that they contain Thumb 
diff --git a/libgcc/config/arm/parity.S b/libgcc/config/arm/parity.S
new file mode 100644
index 00000000000..45233bc9d8f
--- /dev/null
+++ b/libgcc/config/arm/parity.S
@@ -0,0 +1,120 @@ 
+/* parity.S: ARM optimized parity functions
+
+   Copyright (C) 2020-2021 Free Software Foundation, Inc.
+   Contributed by Daniel Engel (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_paritydi2
+
+// int __paritydi2(int)
+// Returns '0' if the number of bits set in $r1:r0 is even, and '1' otherwise.
+// Returns the result in $r0.
+FUNC_START_SECTION paritydi2 .text.sorted.libgcc.paritydi2
+    CFI_START_FUNCTION
+
+        // Combine the upper and lower words, then fall through.
+        // Byte-endianness does not matter for this function.
+        eors    r0,     r1
+
+#endif /* L_paritydi2 */
+
+
+// The implementation of __paritydi2() tightly couples with __paritysi2(),
+//  such that instructions must appear consecutively in the same memory
+//  section for proper flow control.  However, this construction inhibits
+//  the ability to discard __paritydi2() when only using __paritysi2().
+// Therefore, this block configures __paritysi2() for compilation twice.
+// The first version is a minimal standalone implementation, and the second
+//  version is the continuation of __paritydi2().  The standalone version must
+//  be declared WEAK, so that the combined version can supersede it and
+//  provide both symbols when required.
+// '_paritysi2' should appear before '_paritydi2' in LIB1ASMFUNCS.
+#if defined(L_paritysi2) || defined(L_paritydi2)
+
+#ifdef L_paritysi2
+// int __paritysi2(int)
+// Returns '0' if the number of bits set in $r0 is even, and '1' otherwise.
+// Returns the result in $r0.
+// Uses $r2 as scratch space.
+WEAK_START_SECTION paritysi2 .text.sorted.libgcc.paritysi2
+    CFI_START_FUNCTION
+
+#else /* L_paritydi2 */
+FUNC_ENTRY paritysi2
+
+#endif
+
+  #if defined(__thumb__) && __thumb__
+    #if defined(__OPTIMIZE_SIZE__) && __OPTIMIZE_SIZE__
+
+        // Size optimized: 16 bytes, 40 cycles
+        // Speed optimized: 24 bytes, 14 cycles
+        movs    r2,     #16
+
+    LLSYM(__parity_loop):
+        // Calculate the parity of successively smaller half-words into the MSB.
+        movs    r1,     r0
+        lsls    r1,     r2
+        eors    r0,     r1
+        lsrs    r2,     #1
+        bne     LLSYM(__parity_loop)
+
+    #else /* !__OPTIMIZE_SIZE__ */
+
+        // Unroll the loop.  The 'libgcc' reference C implementation replaces
+        //  the x2 and the x1 shifts with a constant.  However, since it takes
+        //  4 cycles to load, index, and mask the constant result, it doesn't
+        //  cost anything to keep shifting (and saves a few bytes).
+        lsls    r1,     r0,     #16
+        eors    r0,     r1
+        lsls    r1,     r0,     #8
+        eors    r0,     r1
+        lsls    r1,     r0,     #4
+        eors    r0,     r1
+        lsls    r1,     r0,     #2
+        eors    r0,     r1
+        lsls    r1,     r0,     #1
+        eors    r0,     r1
+
+    #endif /* !__OPTIMIZE_SIZE__ */
+  #else /* !__thumb__ */
+
+        eors    r0,    r0,     r0,     lsl #16
+        eors    r0,    r0,     r0,     lsl #8
+        eors    r0,    r0,     r0,     lsl #4
+        eors    r0,    r0,     r0,     lsl #2
+        eors    r0,    r0,     r0,     lsl #1
+
+  #endif /* !__thumb__ */
+
+        lsrs    r0,     #31
+        RET
+
+    CFI_END_FUNCTION
+FUNC_END paritysi2
+
+#ifdef L_paritydi2
+FUNC_END paritydi2
+#endif
+
+#endif /* L_paritysi2 || L_paritydi2 */
+
diff --git a/libgcc/config/arm/t-elf b/libgcc/config/arm/t-elf
index 346fc766f17..0e9b9ce21af 100644
--- a/libgcc/config/arm/t-elf
+++ b/libgcc/config/arm/t-elf
@@ -24,6 +24,7 @@  endif # !__symbian__
 LIB1ASMFUNCS += \
         _clzsi2 \
 	_ctzsi2 \
+	_paritysi2 \
 
 
 # Group 1: Integer function objects.
@@ -37,6 +38,7 @@  LIB1ASMFUNCS += \
 	_ctzdi2 \
 	_ffssi2 \
 	_ffsdi2 \
+	_paritydi2 \
 	_dvmd_tls \
 	_divsi3 \
 	_modsi3 \