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 34/34] Add -mpure-code support to the CM0 functions.
Date: Mon, 31 Oct 2022 08:45:29 -0700 [thread overview]
Message-ID: <20221031154529.3627576-35-gnu@danielengel.com> (raw)
In-Reply-To: <20221031154529.3627576-1-gnu@danielengel.com>
gcc/libgcc/ChangeLog:
2022-10-09 Daniel Engel <gnu@danielengel.com>
Makefile.in (MPURE_CODE): New macro defines __PURE_CODE__.
(gcc_compile): Appended MPURE_CODE.
lib1funcs.S (FUNC_START_SECTION): Set flags for __PURE_CODE__.
clz2.S (__clzsi2): Added -mpure-code compatible instructions.
ctz2.S (__ctzsi2): Same.
popcnt.S (__popcountsi2, __popcountdi2): Same.
---
libgcc/Makefile.in | 5 ++++-
libgcc/config/arm/clz2.S | 25 ++++++++++++++++++++++-
libgcc/config/arm/ctz2.S | 38 +++++++++++++++++++++++++++++++++--
libgcc/config/arm/lib1funcs.S | 7 ++++++-
libgcc/config/arm/popcnt.S | 33 +++++++++++++++++++++++++-----
5 files changed, 98 insertions(+), 10 deletions(-)
diff --git a/libgcc/Makefile.in b/libgcc/Makefile.in
index 1fe708a93f7..da2da7046cc 100644
--- a/libgcc/Makefile.in
+++ b/libgcc/Makefile.in
@@ -307,6 +307,9 @@ CRTSTUFF_CFLAGS = -O2 $(GCC_CFLAGS) $(INCLUDES) $(MULTILIB_CFLAGS) -g0 \
# Extra flags to use when compiling crt{begin,end}.o.
CRTSTUFF_T_CFLAGS =
+# Pass the -mpure-code flag into assembly for conditional compilation.
+MPURE_CODE = $(if $(findstring -mpure-code,$(CFLAGS)), -D__PURE_CODE__)
+
MULTIDIR := $(shell $(CC) $(CFLAGS) -print-multi-directory)
MULTIOSDIR := $(shell $(CC) $(CFLAGS) -print-multi-os-directory)
@@ -316,7 +319,7 @@ inst_slibdir = $(slibdir)$(MULTIOSSUBDIR)
gcc_compile_bare = $(CC) $(INTERNAL_CFLAGS) $(CFLAGS-$(<F))
compile_deps = -MT $@ -MD -MP -MF $(basename $@).dep
-gcc_compile = $(gcc_compile_bare) -o $@ $(compile_deps)
+gcc_compile = $(gcc_compile_bare) -o $@ $(compile_deps) $(MPURE_CODE)
gcc_s_compile = $(gcc_compile) -DSHARED
objects = $(filter %$(objext),$^)
diff --git a/libgcc/config/arm/clz2.S b/libgcc/config/arm/clz2.S
index 3d40811278b..4e6665511f3 100644
--- a/libgcc/config/arm/clz2.S
+++ b/libgcc/config/arm/clz2.S
@@ -214,17 +214,40 @@ FUNC_ENTRY clzsi2
IT(sub,ne) r2, #4
LLSYM(__clz2):
+ #if defined(__PURE_CODE__) && __PURE_CODE__
+ // Without access to table data, continue unrolling the loop.
+ lsrs r1, r0, #2
+
+ #ifdef __HAVE_FEATURE_IT
+ do_it ne,t
+ #else
+ beq LLSYM(__clz1)
+ #endif
+
+ // Out of 4 bits, the first '1' is somewhere in the highest 2,
+ // so the lower 2 bits are no longer interesting.
+ IT(mov,ne) r0, r1
+ IT(sub,ne) r2, #2
+
+ LLSYM(__clz1):
+ // Convert remainder {0,1,2,3} to {0,1,2,2}.
+ lsrs r1, r0, #1
+ bics r0, r1
+
+ #else /* !__PURE_CODE__ */
// Load the remainder by index
adr r1, LLSYM(__clz_remainder)
ldrb r0, [r1, r0]
+ #endif /* !__PURE_CODE__ */
#endif /* !__OPTIMIZE_SIZE__ */
// Account for the remainder.
subs r0, r2, r0
RET
- #if !defined(__OPTIMIZE_SIZE__) || !__OPTIMIZE_SIZE__
+ #if !(defined(__OPTIMIZE_SIZE__) && __OPTIMIZE_SIZE__) && \
+ !(defined(__PURE_CODE__) && __PURE_CODE__)
.align 2
LLSYM(__clz_remainder):
.byte 0,1,2,2,3,3,3,3,4,4,4,4,4,4,4,4
diff --git a/libgcc/config/arm/ctz2.S b/libgcc/config/arm/ctz2.S
index d57acabae01..b21485156f6 100644
--- a/libgcc/config/arm/ctz2.S
+++ b/libgcc/config/arm/ctz2.S
@@ -209,11 +209,44 @@ FUNC_ENTRY ctzsi2
IT(sub,ne) r2, #4
LLSYM(__ctz2):
+ #if defined(__PURE_CODE__) && __PURE_CODE__
+ // Without access to table data, continue unrolling the loop.
+ lsls r1, r0, #2
+
+ #ifdef __HAVE_FEATURE_IT
+ do_it ne, t
+ #else
+ beq LLSYM(__ctz1)
+ #endif
+
+ // Out of 4 bits, the first '1' is somewhere in the lowest 2,
+ // so the higher 2 bits are no longer interesting.
+ IT(mov,ne) r0, r1
+ IT(sub,ne) r2, #2
+
+ LLSYM(__ctz1):
+ // Convert remainder {0,1,2,3} in $r0[31:30] to {0,2,1,2}.
+ lsrs r0, #31
+
+ #ifdef __HAVE_FEATURE_IT
+ do_it cs, t
+ #else
+ bcc LLSYM(__ctz_zero)
+ #endif
+
+ // If bit[30] of the remainder is set, neither of these bits count
+ // towards the result. Bit[31] must be cleared.
+ // Otherwise, bit[31] becomes the final remainder.
+ IT(sub,cs) r2, #2
+ IT(eor,cs) r0, r0
+
+ #else /* !__PURE_CODE__ */
// Look up the remainder by index.
lsrs r0, #28
adr r3, LLSYM(__ctz_remainder)
ldrb r0, [r3, r0]
+ #endif /* !__PURE_CODE__ */
#endif /* !__OPTIMIZE_SIZE__ */
LLSYM(__ctz_zero):
@@ -221,8 +254,9 @@ FUNC_ENTRY ctzsi2
subs r0, r2, r0
RET
- #if (!defined(__ARM_FEATURE_CLZ) || !__ARM_FEATURE_CLZ) && \
- (!defined(__OPTIMIZE_SIZE__) || !__OPTIMIZE_SIZE__)
+ #if !(defined(__ARM_FEATURE_CLZ) && __ARM_FEATURE_CLZ) && \
+ !(defined(__OPTIMIZE_SIZE__) && __OPTIMIZE_SIZE__) && \
+ !(defined(__PURE_CODE__) && __PURE_CODE__)
.align 2
LLSYM(__ctz_remainder):
.byte 0,4,3,4,2,4,3,4,1,4,3,4,2,4,3,4
diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S
index 28a5f4d5c86..a15939a78bc 100644
--- a/libgcc/config/arm/lib1funcs.S
+++ b/libgcc/config/arm/lib1funcs.S
@@ -454,7 +454,12 @@ SYM (\name):
Use the *_START_SECTION macros for declarations that the linker should
place in a non-defailt section (e.g. ".rodata", ".text.subsection"). */
.macro FUNC_START_SECTION name section
- .section \section,"x"
+#ifdef __PURE_CODE__
+ /* SHF_ARM_PURECODE | SHF_ALLOC | SHF_EXECINSTR */
+ .section \section,"0x20000006",%progbits
+#else
+ .section \section,"ax",%progbits
+#endif
.align 0
FUNC_ENTRY \name
.endm
diff --git a/libgcc/config/arm/popcnt.S b/libgcc/config/arm/popcnt.S
index 4613ea475b0..7e0878badaa 100644
--- a/libgcc/config/arm/popcnt.S
+++ b/libgcc/config/arm/popcnt.S
@@ -23,6 +23,29 @@
<http://www.gnu.org/licenses/>. */
+#if defined(L_popcountdi2) || defined(L_popcountsi2)
+
+.macro ldmask reg, temp, value
+ #if defined(__PURE_CODE__) && (__PURE_CODE__)
+ #ifdef NOT_ISA_TARGET_32BIT
+ movs \reg, \value
+ lsls \temp, \reg, #8
+ orrs \reg, \temp
+ lsls \temp, \reg, #16
+ orrs \reg, \temp
+ #else
+ // Assumption: __PURE_CODE__ only support M-profile.
+ movw \reg ((\value) * 0x101)
+ movt \reg ((\value) * 0x101)
+ #endif
+ #else
+ ldr \reg, =((\value) * 0x1010101)
+ #endif
+.endm
+
+#endif
+
+
#ifdef L_popcountdi2
// int __popcountdi2(int)
@@ -49,7 +72,7 @@ FUNC_START_SECTION popcountdi2 .text.sorted.libgcc.popcountdi2
#else /* !__OPTIMIZE_SIZE__ */
// Load the one-bit alternating mask.
- ldr r3, =0x55555555
+ ldmask r3, r2, 0x55
// Reduce the second word.
lsrs r2, r1, #1
@@ -62,7 +85,7 @@ FUNC_START_SECTION popcountdi2 .text.sorted.libgcc.popcountdi2
subs r0, r2
// Load the two-bit alternating mask.
- ldr r3, =0x33333333
+ ldmask r3, r2, 0x33
// Reduce the second word.
lsrs r2, r1, #2
@@ -140,7 +163,7 @@ FUNC_ENTRY popcountsi2
#else /* !__OPTIMIZE_SIZE__ */
// Load the one-bit alternating mask.
- ldr r3, =0x55555555
+ ldmask r3, r2, 0x55
// Reduce the word.
lsrs r1, r0, #1
@@ -148,7 +171,7 @@ FUNC_ENTRY popcountsi2
subs r0, r1
// Load the two-bit alternating mask.
- ldr r3, =0x33333333
+ ldmask r3, r2, 0x33
// Reduce the word.
lsrs r1, r0, #2
@@ -158,7 +181,7 @@ FUNC_ENTRY popcountsi2
adds r0, r1
// Load the four-bit alternating mask.
- ldr r3, =0x0F0F0F0F
+ ldmask r3, r2, 0x0F
// Reduce the word.
lsrs r1, r0, #4
--
2.34.1
next prev parent reply other threads:[~2022-10-31 15:49 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 ` [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 ` Daniel Engel [this message]
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=20221031154529.3627576-35-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).