From 7edf70d6b010dd803d324bf90f5241a44bec3df7 Mon Sep 17 00:00:00 2001
From: Manjunath S Matti <mmatti@linux.ibm.com>
Date: Tue, 15 Nov 2022 02:45:53 -0600
Subject: [PATCH 1/3] Preparation for Power optimizations
Optimized functions for Power will make use of GNU indirect functions,
an extension to support different implementations of the same function,
which can be selected during runtime. This will be used to provide
optimized functions for different processor versions.
Since this is a GNU extension, we placed the definition of the Z_IFUNC
macro under `contrib/gcc`. This can be reused by other archs as well.
Author: Matheus Castanho <msc@linux.ibm.com>
Author: Rogerio Alves <rcardoso@linux.ibm.com>
Signed-off-by: Manjunath Matti <mmatti@linux.ibm.com>
---
CMakeLists.txt | 71 ++++++++++++++++++++++++++++++++++++++++++
configure | 66 +++++++++++++++++++++++++++++++++++++++
contrib/README.contrib | 8 +++++
contrib/gcc/zifunc.h | 60 +++++++++++++++++++++++++++++++++++
contrib/power/power.h | 4 +++
5 files changed, 209 insertions(+)
create mode 100644 contrib/gcc/zifunc.h
create mode 100644 contrib/power/power.h
diff --git a/CMakeLists.txt b/CMakeLists.txt
index b412dc7..e313f95 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -5,6 +5,8 @@ project(zlib C)
set(VERSION "1.2.13")
+option(POWER "Enable building power implementation")
+
set(INSTALL_BIN_DIR "${CMAKE_INSTALL_PREFIX}/bin" CACHE PATH "Installation directory for executables")
set(INSTALL_LIB_DIR "${CMAKE_INSTALL_PREFIX}/lib" CACHE PATH "Installation directory for libraries")
set(INSTALL_INC_DIR "${CMAKE_INSTALL_PREFIX}/include" CACHE PATH "Installation directory for headers")
@@ -126,6 +128,75 @@ if(NOT MINGW)
)
endif()
+if(CMAKE_COMPILER_IS_GNUCC)
+
+ # test to see if we can use a GNU indirect function to detect and load optimized code at runtime
+ CHECK_C_SOURCE_COMPILES("
+ static int test_ifunc_native(void)
+ {
+ return 1;
+ }
+ static int (*(check_ifunc_native(void)))(void)
+ {
+ return test_ifunc_native;
+ }
+ int test_ifunc(void) __attribute__ ((ifunc (\"check_ifunc_native\")));
+ int main(void)
+ {
+ return 0;
+ }
+ " HAS_C_ATTR_IFUNC)
+
+ if(HAS_C_ATTR_IFUNC)
+ add_definitions(-DHAVE_IFUNC)
+ set(ZLIB_PRIVATE_HDRS ${ZLIB_PRIVATE_HDRS} contrib/gcc/zifunc.h)
+ endif()
+
+ if(POWER)
+ # Test to see if we can use the optimizations for Power
+ CHECK_C_SOURCE_COMPILES("
+ #ifndef _ARCH_PPC
+ #error \"Target is not Power\"
+ #endif
+ #ifndef __BUILTIN_CPU_SUPPORTS__
+ #error \"Target doesn't support __builtin_cpu_supports()\"
+ #endif
+ int main() { return 0; }
+ " HAS_POWER_SUPPORT)
+
+ if(HAS_POWER_SUPPORT AND HAS_C_ATTR_IFUNC)
+ add_definitions(-DZ_POWER_OPT)
+
+ set(CMAKE_REQUIRED_FLAGS -mcpu=power8)
+ CHECK_C_SOURCE_COMPILES("int main(void){return 0;}" POWER8)
+
+ if(POWER8)
+ add_definitions(-DZ_POWER8)
+ set(ZLIB_POWER8 )
+
+ set_source_files_properties(
+ ${ZLIB_POWER8}
+ PROPERTIES COMPILE_FLAGS -mcpu=power8)
+ endif()
+
+ set(CMAKE_REQUIRED_FLAGS -mcpu=power9)
+ CHECK_C_SOURCE_COMPILES("int main(void){return 0;}" POWER9)
+
+ if(POWER9)
+ add_definitions(-DZ_POWER9)
+ set(ZLIB_POWER9 )
+
+ set_source_files_properties(
+ ${ZLIB_POWER9}
+ PROPERTIES COMPILE_FLAGS -mcpu=power9)
+ endif()
+
+ set(ZLIB_PRIVATE_HDRS ${ZLIB_PRIVATE_HDRS} contrib/power/power.h)
+ set(ZLIB_SRCS ${ZLIB_SRCS} ${ZLIB_POWER8} ${ZLIB_POWER9})
+ endif()
+ endif()
+endif()
+
# parse the full version number from zlib.h and include in ZLIB_FULL_VERSION
file(READ ${CMAKE_CURRENT_SOURCE_DIR}/zlib.h _zlib_h_contents)
string(REGEX REPLACE ".*#define[ \t]+ZLIB_VERSION[ \t]+\"([-0-9A-Za-z.]+)\".*"
diff --git a/configure b/configure
index fa4d5da..9ee7008 100755
--- a/configure
+++ b/configure
@@ -828,6 +828,72 @@ EOF
fi
fi
+# test to see if we can use a gnu indirection function to detect and load optimized code at runtime
+echo >> configure.log
+cat > $test.c <<EOF
+static int test_ifunc_native(void)
+{
+ return 1;
+}
+
+static int (*(check_ifunc_native(void)))(void)
+{
+ return test_ifunc_native;
+}
+
+int test_ifunc(void) __attribute__ ((ifunc ("check_ifunc_native")));
+EOF
+
+if tryboth $CC -c $CFLAGS $test.c; then
+ SFLAGS="${SFLAGS} -DHAVE_IFUNC"
+ CFLAGS="${CFLAGS} -DHAVE_IFUNC"
+ echo "Checking for attribute(ifunc) support... Yes." | tee -a configure.log
+else
+ echo "Checking for attribute(ifunc) support... No." | tee -a configure.log
+fi
+
+# Test to see if we can use the optimizations for Power
+echo >> configure.log
+cat > $test.c <<EOF
+#ifndef _ARCH_PPC
+ #error "Target is not Power"
+#endif
+#ifndef HAVE_IFUNC
+ #error "Target doesn't support ifunc"
+#endif
+#ifndef __BUILTIN_CPU_SUPPORTS__
+ #error "Target doesn't support __builtin_cpu_supports()"
+#endif
+EOF
+
+if tryboth $CC -c $CFLAGS $test.c; then
+ echo "int main(void){return 0;}" > $test.c
+
+ if tryboth $CC -c $CFLAGS -mcpu=power8 $test.c; then
+ POWER8="-DZ_POWER8"
+ PIC_OBJC="${PIC_OBJC}"
+ OBJC="${OBJC}"
+ echo "Checking for -mcpu=power8 support... Yes." | tee -a configure.log
+ else
+ echo "Checking for -mcpu=power8 support... No." | tee -a configure.log
+ fi
+
+ if tryboth $CC -c $CFLAGS -mcpu=power9 $test.c; then
+ POWER9="-DZ_POWER9"
+ PIC_OBJC="${PIC_OBJC}"
+ OBJC="${OBJC}"
+ echo "Checking for -mcpu=power9 support... Yes." | tee -a configure.log
+ else
+ echo "Checking for -mcpu=power9 support... No." | tee -a configure.log
+ fi
+
+ SFLAGS="${SFLAGS} ${POWER8} ${POWER9} -DZ_POWER_OPT"
+ CFLAGS="${CFLAGS} ${POWER8} ${POWER9} -DZ_POWER_OPT"
+ echo "Checking for Power optimizations support... Yes." | tee -a configure.log
+else
+ echo "Checking for Power optimizations support... No." | tee -a configure.log
+fi
+
# show the results in the log
echo >> configure.log
echo ALL = $ALL >> configure.log
diff --git a/contrib/README.contrib b/contrib/README.contrib
index 5e5f950..c57b520 100644
--- a/contrib/README.contrib
+++ b/contrib/README.contrib
@@ -11,6 +11,10 @@ ada/ by Dmitriy Anisimkov <anisimkov@yahoo.com>
blast/ by Mark Adler <madler@alumni.caltech.edu>
Decompressor for output of PKWare Data Compression Library (DCL)
+gcc/ by Matheus Castanho <msc@linux.ibm.com>
+ and Rogerio Alves <rcardoso@linux.ibm.com>
+ Optimization helpers using GCC-specific extensions
+
delphi/ by Cosmin Truta <cosmint@cs.ubbcluj.ro>
Support for Delphi and C++ Builder
@@ -42,6 +46,10 @@ minizip/ by Gilles Vollant <info@winimage.com>
pascal/ by Bob Dellaca <bobdl@xtra.co.nz> et al.
Support for Pascal
+power/ by Matheus Castanho <msc@linux.ibm.com>
+ and Rogerio Alves <rcardoso@linux.ibm.com>
+ Optimized functions for Power processors
+
puff/ by Mark Adler <madler@alumni.caltech.edu>
Small, low memory usage inflate. Also serves to provide an
unambiguous description of the deflate format.
diff --git a/contrib/gcc/zifunc.h b/contrib/gcc/zifunc.h
new file mode 100644
index 0000000..daf4fe4
--- /dev/null
+++ b/contrib/gcc/zifunc.h
@@ -0,0 +1,60 @@
+/* Copyright (C) 2019 Matheus Castanho <msc@linux.ibm.com>, IBM
+ * 2019 Rogerio Alves <rogerio.alves@ibm.com>, IBM
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+#ifndef Z_IFUNC_H_
+#define Z_IFUNC_H_
+
+/* Helpers for arch optimizations */
+
+#define Z_IFUNC(fname) \
+ typeof(fname) fname __attribute__ ((ifunc (#fname "_resolver"))); \
+ local typeof(fname) *fname##_resolver(void)
+/* This is a helper macro to declare a resolver for an indirect function
+ * (ifunc). Let's say you have function
+ *
+ * int foo (int a);
+ *
+ * for which you want to provide different implementations, for example:
+ *
+ * int foo_clever (int a) {
+ * ... clever things ...
+ * }
+ *
+ * int foo_smart (int a) {
+ * ... smart things ...
+ * }
+ *
+ * You will have to declare foo() as an indirect function and also provide a
+ * resolver for it, to choose between foo_clever() and foo_smart() based on
+ * some criteria you define (e.g. processor features).
+ *
+ * Since most likely foo() has a default implementation somewhere in zlib, you
+ * may have to rename it so the 'foo' symbol can be used by the ifunc without
+ * conflicts.
+ *
+ * #define foo foo_default
+ * int foo (int a) {
+ * ...
+ * }
+ * #undef foo
+ *
+ * Now you just have to provide a resolver function to choose which function
+ * should be used (decided at runtime on the first call to foo()):
+ *
+ * Z_IFUNC(foo) {
+ * if (... some condition ...)
+ * return foo_clever;
+ *
+ * if (... other condition ...)
+ * return foo_smart;
+ *
+ * return foo_default;
+ * }
+ *
+ * All calls to foo() throughout the code can remain untouched, all the magic
+ * will be done by the linker using the resolver function.
+ */
+
+#endif /* Z_IFUNC_H_ */
diff --git a/contrib/power/power.h b/contrib/power/power.h
new file mode 100644
index 0000000..b42c7d6
--- /dev/null
+++ b/contrib/power/power.h
@@ -0,0 +1,4 @@
+/* Copyright (C) 2019 Matheus Castanho <msc@linux.ibm.com>, IBM
+ * 2019 Rogerio Alves <rogerio.alves@ibm.com>, IBM
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
--
2.37.3
From 2b843de4ffa241edc20877f3ec47e75c9ed13ec8 Mon Sep 17 00:00:00 2001
From: Manjunath S Matti <mmatti@linux.ibm.com>
Date: Wed, 16 Nov 2022 03:53:53 -0600
Subject: [PATCH 2/3] Add Power8+ optimized crc32
This commit adds an optimized version for the crc32 function based
on crc32-vpmsum from https://github.com/antonblanchard/crc32-vpmsum/
This is the C implementation created by Rogerio Alves
<rogealve@br.ibm.com>
It makes use of vector instructions to speed up CRC32 algorithm.
Author: Rogerio Alves <rcardoso@linux.ibm.com>
Signed-off-by: Manjunath Matti <mmatti@linux.ibm.com>
---
.gitignore | 3 +
CMakeLists.txt | 7 +-
Makefile.in | 43 +-
configure | 7 +-
contrib/README.contrib | 3 +-
contrib/power/clang_workaround.h | 82 ++
contrib/power/crc32_constants.h | 1206 ++++++++++++++++++++++++++++++
contrib/power/crc32_z_power8.c | 679 +++++++++++++++++
contrib/power/crc32_z_resolver.c | 15 +
contrib/power/power.h | 4 +
crc32.c | 12 +
test/crc32_test.c | 205 +++++
12 files changed, 2252 insertions(+), 14 deletions(-)
create mode 100644 contrib/power/clang_workaround.h
create mode 100644 contrib/power/crc32_constants.h
create mode 100644 contrib/power/crc32_z_power8.c
create mode 100644 contrib/power/crc32_z_resolver.c
create mode 100644 test/crc32_test.c
diff --git a/CMakeLists.txt b/CMakeLists.txt
index e313f95..4ba992b 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -172,7 +172,8 @@ if(CMAKE_COMPILER_IS_GNUCC)
if(POWER8)
add_definitions(-DZ_POWER8)
- set(ZLIB_POWER8 )
+ set(ZLIB_POWER8
+ contrib/power/crc32_z_power8.c)
set_source_files_properties(
${ZLIB_POWER8}
@@ -269,6 +270,10 @@ add_executable(example test/example.c)
target_link_libraries(example zlib)
add_test(example example)
+add_executable(crc32_test test/crc32_test.c)
+target_link_libraries(crc32_test zlib)
+add_test(crc32_test crc32_test)
+
add_executable(minigzip test/minigzip.c)
target_link_libraries(minigzip zlib)
diff --git a/Makefile.in b/Makefile.in
index 7d2713f..408954d 100644
--- a/Makefile.in
+++ b/Makefile.in
@@ -71,11 +71,11 @@ PIC_OBJS = $(PIC_OBJC) $(PIC_OBJA)
all: static shared
-static: example$(EXE) minigzip$(EXE)
+static: crc32_test$(EXE) example$(EXE) minigzip$(EXE)
-shared: examplesh$(EXE) minigzipsh$(EXE)
+shared: crc32_testsh$(EXE) examplesh$(EXE) minigzipsh$(EXE)
-all64: example64$(EXE) minigzip64$(EXE)
+all64: crc32_test64$(EXE) example64$(EXE) minigzip64$(EXE)
check: test
@@ -83,7 +83,7 @@ test: all teststatic testshared
teststatic: static
@TMPST=tmpst_$$; \
- if echo hello world | ${QEMU_RUN} ./minigzip | ${QEMU_RUN} ./minigzip -d && ${QEMU_RUN} ./example $$TMPST ; then \
+ if echo hello world | ${QEMU_RUN} ./minigzip | ${QEMU_RUN} ./minigzip -d && ${QEMU_RUN} ./example $$TMPST && ${QEMU_RUN} ./crc32_test; then \
echo ' *** zlib test OK ***'; \
else \
echo ' *** zlib test FAILED ***'; false; \
@@ -96,7 +96,7 @@ testshared: shared
DYLD_LIBRARY_PATH=`pwd`:$(DYLD_LIBRARY_PATH) ; export DYLD_LIBRARY_PATH; \
SHLIB_PATH=`pwd`:$(SHLIB_PATH) ; export SHLIB_PATH; \
TMPSH=tmpsh_$$; \
- if echo hello world | ${QEMU_RUN} ./minigzipsh | ${QEMU_RUN} ./minigzipsh -d && ${QEMU_RUN} ./examplesh $$TMPSH; then \
+ if echo hello world | ${QEMU_RUN} ./minigzipsh | ${QEMU_RUN} ./minigzipsh -d && ${QEMU_RUN} ./examplesh $$TMPSH && ${QEMU_RUN} ./crc32_testsh; then \
echo ' *** zlib shared test OK ***'; \
else \
echo ' *** zlib shared test FAILED ***'; false; \
@@ -105,7 +105,7 @@ testshared: shared
test64: all64
@TMP64=tmp64_$$; \
- if echo hello world | ${QEMU_RUN} ./minigzip64 | ${QEMU_RUN} ./minigzip64 -d && ${QEMU_RUN} ./example64 $$TMP64; then \
+ if echo hello world | ${QEMU_RUN} ./minigzip64 | ${QEMU_RUN} ./minigzip64 -d && ${QEMU_RUN} ./example64 $$TMP64 && ${QEMU_RUN} ./crc32_test64; then \
echo ' *** zlib 64-bit test OK ***'; \
else \
echo ' *** zlib 64-bit test FAILED ***'; false; \
@@ -139,12 +139,18 @@ match.lo: match.S
mv _match.o match.lo
rm -f _match.s
+crc32_test.o: $(SRCDIR)test/crc32_test.c $(SRCDIR)zlib.h zconf.h
+ $(CC) $(CFLAGS) $(ZINCOUT) -c -o $@ $(SRCDIR)test/crc32_test.c
+
example.o: $(SRCDIR)test/example.c $(SRCDIR)zlib.h zconf.h
$(CC) $(CFLAGS) $(ZINCOUT) -c -o $@ $(SRCDIR)test/example.c
minigzip.o: $(SRCDIR)test/minigzip.c $(SRCDIR)zlib.h zconf.h
$(CC) $(CFLAGS) $(ZINCOUT) -c -o $@ $(SRCDIR)test/minigzip.c
+crc32_test64.o: $(SRCDIR)test/crc32_test.c $(SRCDIR)zlib.h zconf.h
+ $(CC) $(CFLAGS) $(ZINCOUT) -D_FILE_OFFSET_BITS=64 -c -o $@ $(SRCDIR)test/crc32_test.c
+
example64.o: $(SRCDIR)test/example.c $(SRCDIR)zlib.h zconf.h
$(CC) $(CFLAGS) $(ZINCOUT) -D_FILE_OFFSET_BITS=64 -c -o $@ $(SRCDIR)test/example.c
@@ -158,6 +164,9 @@ adler32.o: $(SRCDIR)adler32.c
crc32.o: $(SRCDIR)crc32.c
$(CC) $(CFLAGS) $(ZINC) -c -o $@ $(SRCDIR)crc32.c
+crc32_z_power8.o: $(SRCDIR)contrib/power/crc32_z_power8.c
+ $(CC) $(CFLAGS) -mcpu=power8 $(ZINC) -c -o $@ $(SRCDIR)contrib/power/crc32_z_power8.c
+
deflate.o: $(SRCDIR)deflate.c
$(CC) $(CFLAGS) $(ZINC) -c -o $@ $(SRCDIR)deflate.c
@@ -208,6 +217,11 @@ crc32.lo: $(SRCDIR)crc32.c
$(CC) $(SFLAGS) $(ZINC) -DPIC -c -o objs/crc32.o $(SRCDIR)crc32.c
-@mv objs/crc32.o $@
+crc32_z_power8.lo: $(SRCDIR)contrib/power/crc32_z_power8.c
+ -@mkdir objs 2>/dev/null || test -d objs
+ $(CC) $(SFLAGS) -mcpu=power8 $(ZINC) -DPIC -c -o objs/crc32_z_power8.o $(SRCDIR)contrib/power/crc32_z_power8.c
+ -@mv objs/crc32_z_power8.o $@
+
deflate.lo: $(SRCDIR)deflate.c
-@mkdir objs 2>/dev/null || test -d objs
$(CC) $(SFLAGS) $(ZINC) -DPIC -c -o objs/deflate.o $(SRCDIR)deflate.c
@@ -281,18 +295,27 @@ placebo $(SHAREDLIBV): $(PIC_OBJS) libz.a
ln -s $@ $(SHAREDLIBM)
-@rmdir objs
+crc32_test$(EXE): crc32_test.o $(STATICLIB)
+ $(CC) $(CFLAGS) -o $@ crc32_test.o $(TEST_LDFLAGS)
+
example$(EXE): example.o $(STATICLIB)
$(CC) $(CFLAGS) -o $@ example.o $(TEST_LDFLAGS)
minigzip$(EXE): minigzip.o $(STATICLIB)
$(CC) $(CFLAGS) -o $@ minigzip.o $(TEST_LDFLAGS)
+crc32_testsh$(EXE): crc32_test.o $(SHAREDLIBV)
+ $(CC) $(CFLAGS) -o $@ crc32_test.o -L. $(SHAREDLIBV)
+
examplesh$(EXE): example.o $(SHAREDLIBV)
$(CC) $(CFLAGS) -o $@ example.o $(LDFLAGS) -L. $(SHAREDLIBV)
minigzipsh$(EXE): minigzip.o $(SHAREDLIBV)
$(CC) $(CFLAGS) -o $@ minigzip.o $(LDFLAGS) -L. $(SHAREDLIBV)
+crc32_test64$(EXE): crc32_test64.o $(STATICLIB)
+ $(CC) $(CFLAGS) -o $@ crc32_test64.o $(TEST_LDFLAGS)
+
example64$(EXE): example64.o $(STATICLIB)
$(CC) $(CFLAGS) -o $@ example64.o $(TEST_LDFLAGS)
@@ -362,8 +385,8 @@ zconf: $(SRCDIR)zconf.h.in
mostlyclean: clean
clean:
rm -f *.o *.lo *~ \
- example$(EXE) minigzip$(EXE) examplesh$(EXE) minigzipsh$(EXE) \
- example64$(EXE) minigzip64$(EXE) \
+ crc32_test$(EXE) example$(EXE) minigzip$(EXE) crc32_testsh$(EXE) examplesh$(EXE) minigzipsh$(EXE) \
+ crc32_test64$(EXE) example64$(EXE) minigzip64$(EXE) \
infcover \
libz.* foo.gz so_locations \
_match.s maketree contrib/infback9/*.o
@@ -385,7 +408,7 @@ tags:
adler32.o zutil.o: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h
gzclose.o gzlib.o gzread.o gzwrite.o: $(SRCDIR)zlib.h zconf.h $(SRCDIR)gzguts.h
-compress.o example.o minigzip.o uncompr.o: $(SRCDIR)zlib.h zconf.h
+compress.o crc32_test.o example.o minigzip.o uncompr.o: $(SRCDIR)zlib.h zconf.h
crc32.o: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)crc32.h
deflate.o: $(SRCDIR)deflate.h $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h
infback.o inflate.o: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)inftrees.h $(SRCDIR)inflate.h $(SRCDIR)inffast.h $(SRCDIR)inffixed.h
@@ -395,7 +418,7 @@ trees.o: $(SRCDIR)deflate.h $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)tr
adler32.lo zutil.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h
gzclose.lo gzlib.lo gzread.lo gzwrite.lo: $(SRCDIR)zlib.h zconf.h $(SRCDIR)gzguts.h
-compress.lo example.lo minigzip.lo uncompr.lo: $(SRCDIR)zlib.h zconf.h
+compress.lo crc32_test.lo example.lo minigzip.lo uncompr.lo: $(SRCDIR)zlib.h zconf.h
crc32.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)crc32.h
deflate.lo: $(SRCDIR)deflate.h $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h
infback.lo inflate.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)inftrees.h $(SRCDIR)inflate.h $(SRCDIR)inffast.h $(SRCDIR)inffixed.h
diff --git a/configure b/configure
index 9ee7008..45d51e5 100755
--- a/configure
+++ b/configure
@@ -858,6 +858,9 @@ cat > $test.c <<EOF
#ifndef _ARCH_PPC
#error "Target is not Power"
#endif
+#if !(defined(__PPC64__) || defined(__powerpc64__))
+ #error "Target is not 64 bits"
+#endif
#ifndef HAVE_IFUNC
#error "Target doesn't support ifunc"
#endif
@@ -871,8 +874,8 @@ if tryboth $CC -c $CFLAGS $test.c; then
if tryboth $CC -c $CFLAGS -mcpu=power8 $test.c; then
POWER8="-DZ_POWER8"
- PIC_OBJC="${PIC_OBJC}"
- OBJC="${OBJC}"
+ PIC_OBJC="${PIC_OBJC} crc32_z_power8.lo"
+ OBJC="${OBJC} crc32_z_power8.o"
echo "Checking for -mcpu=power8 support... Yes." | tee -a configure.log
else
echo "Checking for -mcpu=power8 support... No." | tee -a configure.log
diff --git a/contrib/README.contrib b/contrib/README.contrib
index c57b520..90170df 100644
--- a/contrib/README.contrib
+++ b/contrib/README.contrib
@@ -46,7 +46,8 @@ minizip/ by Gilles Vollant <info@winimage.com>
pascal/ by Bob Dellaca <bobdl@xtra.co.nz> et al.
Support for Pascal
-power/ by Matheus Castanho <msc@linux.ibm.com>
+power/ by Daniel Black <daniel@linux.ibm.com>
+ Matheus Castanho <msc@linux.ibm.com>
and Rogerio Alves <rcardoso@linux.ibm.com>
Optimized functions for Power processors
diff --git a/contrib/power/clang_workaround.h b/contrib/power/clang_workaround.h
new file mode 100644
index 0000000..b5e7dae
--- /dev/null
+++ b/contrib/power/clang_workaround.h
@@ -0,0 +1,82 @@
+#ifndef CLANG_WORKAROUNDS_H
+#define CLANG_WORKAROUNDS_H
+
+/*
+ * These stubs fix clang incompatibilities with GCC builtins.
+ */
+
+#ifndef __builtin_crypto_vpmsumw
+#define __builtin_crypto_vpmsumw __builtin_crypto_vpmsumb
+#endif
+#ifndef __builtin_crypto_vpmsumd
+#define __builtin_crypto_vpmsumd __builtin_crypto_vpmsumb
+#endif
+
+static inline
+__vector unsigned long long __attribute__((overloadable))
+vec_ld(int __a, const __vector unsigned long long* __b)
+{
+ return (__vector unsigned long long)__builtin_altivec_lvx(__a, __b);
+}
+
+/*
+ * GCC __builtin_pack_vector_int128 returns a vector __int128_t but Clang
+ * does not recognize this type. On GCC this builtin is translated to a
+ * xxpermdi instruction that only moves the registers __a, __b instead generates
+ * a load.
+ *
+ * Clang has vec_xxpermdi intrinsics. It was implemented in 4.0.0.
+ */
+static inline
+__vector unsigned long long __builtin_pack_vector (unsigned long __a,
+ unsigned long __b)
+{
+ #if defined(__BIG_ENDIAN__)
+ __vector unsigned long long __v = {__a, __b};
+ #else
+ __vector unsigned long long __v = {__b, __a};
+ #endif
+ return __v;
+}
+
+#ifndef vec_xxpermdi
+
+static inline
+unsigned long __builtin_unpack_vector (__vector unsigned long long __v,
+ int __o)
+{
+ return __v[__o];
+}
+
+#if defined(__BIG_ENDIAN__)
+#define __builtin_unpack_vector_0(a) __builtin_unpack_vector ((a), 0)
+#define __builtin_unpack_vector_1(a) __builtin_unpack_vector ((a), 1)
+#else
+#define __builtin_unpack_vector_0(a) __builtin_unpack_vector ((a), 1)
+#define __builtin_unpack_vector_1(a) __builtin_unpack_vector ((a), 0)
+#endif
+
+#else
+
+static inline
+unsigned long __builtin_unpack_vector_0 (__vector unsigned long long __v)
+{
+ #if defined(__BIG_ENDIAN__)
+ return vec_xxpermdi(__v, __v, 0x0)[1];
+ #else
+ return vec_xxpermdi(__v, __v, 0x0)[0];
+ #endif
+}
+
+static inline
+unsigned long __builtin_unpack_vector_1 (__vector unsigned long long __v)
+{
+ #if defined(__BIG_ENDIAN__)
+ return vec_xxpermdi(__v, __v, 0x3)[1];
+ #else
+ return vec_xxpermdi(__v, __v, 0x3)[0];
+ #endif
+}
+#endif /* vec_xxpermdi */
+
+#endif
diff --git a/contrib/power/crc32_constants.h b/contrib/power/crc32_constants.h
new file mode 100644
index 0000000..58088dc
--- /dev/null
+++ b/contrib/power/crc32_constants.h
@@ -0,0 +1,1206 @@
+/*
+*
+* THIS FILE IS GENERATED WITH
+./crc32_constants -c -r -x 0x04C11DB7
+
+* This is from https://github.com/antonblanchard/crc32-vpmsum/
+* DO NOT MODIFY IT MANUALLY!
+*
+*/
+
+#define CRC 0x4c11db7
+#define CRC_XOR
+#define REFLECT
+#define MAX_SIZE 32768
+
+#ifndef __ASSEMBLER__
+#ifdef CRC_TABLE
+static const unsigned int crc_table[] = {
+ 0x00000000, 0x77073096, 0xee0e612c, 0x990951ba,
+ 0x076dc419, 0x706af48f, 0xe963a535, 0x9e6495a3,
+ 0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988,
+ 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91,
+ 0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de,
+ 0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7,
+ 0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec,
+ 0x14015c4f, 0x63066cd9, 0xfa0f3d63, 0x8d080df5,
+ 0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172,
+ 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b,
+ 0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940,
+ 0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59,
+ 0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116,
+ 0x21b4f4b5, 0x56b3c423, 0xcfba9599, 0xb8bda50f,
+ 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
+ 0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d,
+ 0x76dc4190, 0x01db7106, 0x98d220bc, 0xefd5102a,
+ 0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433,
+ 0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818,
+ 0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01,
+ 0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e,
+ 0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457,
+ 0x65b0d9c6, 0x12b7e950, 0x8bbeb8ea, 0xfcb9887c,
+ 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65,
+ 0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2,
+ 0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb,
+ 0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0,
+ 0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9,
+ 0x5005713c, 0x270241aa, 0xbe0b1010, 0xc90c2086,
+ 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
+ 0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4,
+ 0x59b33d17, 0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad,
+ 0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a,
+ 0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683,
+ 0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8,
+ 0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1,
+ 0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe,
+ 0xf762575d, 0x806567cb, 0x196c3671, 0x6e6b06e7,
+ 0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc,
+ 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5,
+ 0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252,
+ 0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b,
+ 0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60,
+ 0xdf60efc3, 0xa867df55, 0x316e8eef, 0x4669be79,
+ 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
+ 0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f,
+ 0xc5ba3bbe, 0xb2bd0b28, 0x2bb45a92, 0x5cb36a04,
+ 0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d,
+ 0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a,
+ 0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713,
+ 0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38,
+ 0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21,
+ 0x86d3d2d4, 0xf1d4e242, 0x68ddb3f8, 0x1fda836e,
+ 0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777,
+ 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c,
+ 0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45,
+ 0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2,
+ 0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db,
+ 0xaed16a4a, 0xd9d65adc, 0x40df0b66, 0x37d83bf0,
+ 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
+ 0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6,
+ 0xbad03605, 0xcdd70693, 0x54de5729, 0x23d967bf,
+ 0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94,
+ 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d,};
+
+#endif /* CRC_TABLE */
+#ifdef POWER8_INTRINSICS
+
+/* Constants */
+
+/* Reduce 262144 kbits to 1024 bits */
+static const __vector unsigned long long vcrc_const[255]
+ __attribute__((aligned (16))) = {
+#ifdef __LITTLE_ENDIAN__
+ /* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */
+ { 0x0000000099ea94a8, 0x00000001651797d2 },
+ /* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */
+ { 0x00000000945a8420, 0x0000000021e0d56c },
+ /* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */
+ { 0x0000000030762706, 0x000000000f95ecaa },
+ /* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */
+ { 0x00000001a52fc582, 0x00000001ebd224ac },
+ /* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */
+ { 0x00000001a4a7167a, 0x000000000ccb97ca },
+ /* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */
+ { 0x000000000c18249a, 0x00000001006ec8a8 },
+ /* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */
+ { 0x00000000a924ae7c, 0x000000014f58f196 },
+ /* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */
+ { 0x00000001e12ccc12, 0x00000001a7192ca6 },
+ /* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */
+ { 0x00000000a0b9d4ac, 0x000000019a64bab2 },
+ /* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */
+ { 0x0000000095e8ddfe, 0x0000000014f4ed2e },
+ /* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */
+ { 0x00000000233fddc4, 0x000000011092b6a2 },
+ /* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */
+ { 0x00000001b4529b62, 0x00000000c8a1629c },
+ /* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */
+ { 0x00000001a7fa0e64, 0x000000017bf32e8e },
+ /* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */
+ { 0x00000001b5334592, 0x00000001f8cc6582 },
+ /* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */
+ { 0x000000011f8ee1b4, 0x000000008631ddf0 },
+ /* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */
+ { 0x000000006252e632, 0x000000007e5a76d0 },
+ /* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */
+ { 0x00000000ab973e84, 0x000000002b09b31c },
+ /* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */
+ { 0x000000007734f5ec, 0x00000001b2df1f84 },
+ /* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */
+ { 0x000000007c547798, 0x00000001d6f56afc },
+ /* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */
+ { 0x000000007ec40210, 0x00000001b9b5e70c },
+ /* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */
+ { 0x00000001ab1695a8, 0x0000000034b626d2 },
+ /* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */
+ { 0x0000000090494bba, 0x000000014c53479a },
+ /* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */
+ { 0x00000001123fb816, 0x00000001a6d179a4 },
+ /* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */
+ { 0x00000001e188c74c, 0x000000015abd16b4 },
+ /* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */
+ { 0x00000001c2d3451c, 0x00000000018f9852 },
+ /* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */
+ { 0x00000000f55cf1ca, 0x000000001fb3084a },
+ /* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */
+ { 0x00000001a0531540, 0x00000000c53dfb04 },
+ /* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */
+ { 0x0000000132cd7ebc, 0x00000000e10c9ad6 },
+ /* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */
+ { 0x0000000073ab7f36, 0x0000000025aa994a },
+ /* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */
+ { 0x0000000041aed1c2, 0x00000000fa3a74c4 },
+ /* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */
+ { 0x0000000136c53800, 0x0000000033eb3f40 },
+ /* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */
+ { 0x0000000126835a30, 0x000000017193f296 },
+ /* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */
+ { 0x000000006241b502, 0x0000000043f6c86a },
+ /* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */
+ { 0x00000000d5196ad4, 0x000000016b513ec6 },
+ /* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */
+ { 0x000000009cfa769a, 0x00000000c8f25b4e },
+ /* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */
+ { 0x00000000920e5df4, 0x00000001a45048ec },
+ /* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */
+ { 0x0000000169dc310e, 0x000000000c441004 },
+ /* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */
+ { 0x0000000009fc331c, 0x000000000e17cad6 },
+ /* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */
+ { 0x000000010d94a81e, 0x00000001253ae964 },
+ /* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */
+ { 0x0000000027a20ab2, 0x00000001d7c88ebc },
+ /* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */
+ { 0x0000000114f87504, 0x00000001e7ca913a },
+ /* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */
+ { 0x000000004b076d96, 0x0000000033ed078a },
+ /* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */
+ { 0x00000000da4d1e74, 0x00000000e1839c78 },
+ /* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */
+ { 0x000000001b81f672, 0x00000001322b267e },
+ /* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */
+ { 0x000000009367c988, 0x00000000638231b6 },
+ /* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */
+ { 0x00000001717214ca, 0x00000001ee7f16f4 },
+ /* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */
+ { 0x000000009f47d820, 0x0000000117d9924a },
+ /* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */
+ { 0x000000010d9a47d2, 0x00000000e1a9e0c4 },
+ /* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */
+ { 0x00000000a696c58c, 0x00000001403731dc },
+ /* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */
+ { 0x000000002aa28ec6, 0x00000001a5ea9682 },
+ /* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */
+ { 0x00000001fe18fd9a, 0x0000000101c5c578 },
+ /* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */
+ { 0x000000019d4fc1ae, 0x00000000dddf6494 },
+ /* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */
+ { 0x00000001ba0e3dea, 0x00000000f1c3db28 },
+ /* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */
+ { 0x0000000074b59a5e, 0x000000013112fb9c },
+ /* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */
+ { 0x00000000f2b5ea98, 0x00000000b680b906 },
+ /* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */
+ { 0x0000000187132676, 0x000000001a282932 },
+ /* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */
+ { 0x000000010a8c6ad4, 0x0000000089406e7e },
+ /* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */
+ { 0x00000001e21dfe70, 0x00000001def6be8c },
+ /* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */
+ { 0x00000001da0050e4, 0x0000000075258728 },
+ /* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */
+ { 0x00000000772172ae, 0x000000019536090a },
+ /* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */
+ { 0x00000000e47724aa, 0x00000000f2455bfc },
+ /* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */
+ { 0x000000003cd63ac4, 0x000000018c40baf4 },
+ /* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */
+ { 0x00000001bf47d352, 0x000000004cd390d4 },
+ /* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */
+ { 0x000000018dc1d708, 0x00000001e4ece95a },
+ /* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */
+ { 0x000000002d4620a4, 0x000000001a3ee918 },
+ /* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */
+ { 0x0000000058fd1740, 0x000000007c652fb8 },
+ /* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */
+ { 0x00000000dadd9bfc, 0x000000011c67842c },
+ /* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */
+ { 0x00000001ea2140be, 0x00000000254f759c },
+ /* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */
+ { 0x000000009de128ba, 0x000000007ece94ca },
+ /* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */
+ { 0x000000013ac3aa8e, 0x0000000038f258c2 },
+ /* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */
+ { 0x0000000099980562, 0x00000001cdf17b00 },
+ /* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */
+ { 0x00000001c1579c86, 0x000000011f882c16 },
+ /* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */
+ { 0x0000000068dbbf94, 0x0000000100093fc8 },
+ /* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */
+ { 0x000000004509fb04, 0x00000001cd684f16 },
+ /* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */
+ { 0x00000001202f6398, 0x000000004bc6a70a },
+ /* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */
+ { 0x000000013aea243e, 0x000000004fc7e8e4 },
+ /* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */
+ { 0x00000001b4052ae6, 0x0000000130103f1c },
+ /* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */
+ { 0x00000001cd2a0ae8, 0x0000000111b0024c },
+ /* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */
+ { 0x00000001fe4aa8b4, 0x000000010b3079da },
+ /* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */
+ { 0x00000001d1559a42, 0x000000010192bcc2 },
+ /* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */
+ { 0x00000001f3e05ecc, 0x0000000074838d50 },
+ /* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */
+ { 0x0000000104ddd2cc, 0x000000001b20f520 },
+ /* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */
+ { 0x000000015393153c, 0x0000000050c3590a },
+ /* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */
+ { 0x0000000057e942c6, 0x00000000b41cac8e },
+ /* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */
+ { 0x000000012c633850, 0x000000000c72cc78 },
+ /* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */
+ { 0x00000000ebcaae4c, 0x0000000030cdb032 },
+ /* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */
+ { 0x000000013ee532a6, 0x000000013e09fc32 },
+ /* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */
+ { 0x00000001bf0cbc7e, 0x000000001ed624d2 },
+ /* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */
+ { 0x00000000d50b7a5a, 0x00000000781aee1a },
+ /* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */
+ { 0x0000000002fca6e8, 0x00000001c4d8348c },
+ /* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */
+ { 0x000000007af40044, 0x0000000057a40336 },
+ /* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */
+ { 0x0000000016178744, 0x0000000085544940 },
+ /* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */
+ { 0x000000014c177458, 0x000000019cd21e80 },
+ /* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */
+ { 0x000000011b6ddf04, 0x000000013eb95bc0 },
+ /* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */
+ { 0x00000001f3e29ccc, 0x00000001dfc9fdfc },
+ /* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */
+ { 0x0000000135ae7562, 0x00000000cd028bc2 },
+ /* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */
+ { 0x0000000190ef812c, 0x0000000090db8c44 },
+ /* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */
+ { 0x0000000067a2c786, 0x000000010010a4ce },
+ /* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */
+ { 0x0000000048b9496c, 0x00000001c8f4c72c },
+ /* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */
+ { 0x000000015a422de6, 0x000000001c26170c },
+ /* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */
+ { 0x00000001ef0e3640, 0x00000000e3fccf68 },
+ /* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */
+ { 0x00000001006d2d26, 0x00000000d513ed24 },
+ /* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */
+ { 0x00000001170d56d6, 0x00000000141beada },
+ /* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */
+ { 0x00000000a5fb613c, 0x000000011071aea0 },
+ /* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */
+ { 0x0000000040bbf7fc, 0x000000012e19080a },
+ /* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */
+ { 0x000000016ac3a5b2, 0x0000000100ecf826 },
+ /* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */
+ { 0x00000000abf16230, 0x0000000069b09412 },
+ /* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */
+ { 0x00000001ebe23fac, 0x0000000122297bac },
+ /* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */
+ { 0x000000008b6a0894, 0x00000000e9e4b068 },
+ /* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */
+ { 0x00000001288ea478, 0x000000004b38651a },
+ /* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */
+ { 0x000000016619c442, 0x00000001468360e2 },
+ /* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */
+ { 0x0000000086230038, 0x00000000121c2408 },
+ /* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */
+ { 0x000000017746a756, 0x00000000da7e7d08 },
+ /* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */
+ { 0x0000000191b8f8f8, 0x00000001058d7652 },
+ /* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */
+ { 0x000000008e167708, 0x000000014a098a90 },
+ /* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */
+ { 0x0000000148b22d54, 0x0000000020dbe72e },
+ /* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */
+ { 0x0000000044ba2c3c, 0x000000011e7323e8 },
+ /* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */
+ { 0x00000000b54d2b52, 0x00000000d5d4bf94 },
+ /* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */
+ { 0x0000000005a4fd8a, 0x0000000199d8746c },
+ /* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */
+ { 0x0000000139f9fc46, 0x00000000ce9ca8a0 },
+ /* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */
+ { 0x000000015a1fa824, 0x00000000136edece },
+ /* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */
+ { 0x000000000a61ae4c, 0x000000019b92a068 },
+ /* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */
+ { 0x0000000145e9113e, 0x0000000071d62206 },
+ /* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */
+ { 0x000000006a348448, 0x00000000dfc50158 },
+ /* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */
+ { 0x000000004d80a08c, 0x00000001517626bc },
+ /* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */
+ { 0x000000014b6837a0, 0x0000000148d1e4fa },
+ /* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */
+ { 0x000000016896a7fc, 0x0000000094d8266e },
+ /* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */
+ { 0x000000014f187140, 0x00000000606c5e34 },
+ /* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */
+ { 0x000000019581b9da, 0x000000019766beaa },
+ /* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */
+ { 0x00000001091bc984, 0x00000001d80c506c },
+ /* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */
+ { 0x000000001067223c, 0x000000001e73837c },
+ /* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */
+ { 0x00000001ab16ea02, 0x0000000064d587de },
+ /* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */
+ { 0x000000013c4598a8, 0x00000000f4a507b0 },
+ /* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */
+ { 0x00000000b3735430, 0x0000000040e342fc },
+ /* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */
+ { 0x00000001bb3fc0c0, 0x00000001d5ad9c3a },
+ /* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */
+ { 0x00000001570ae19c, 0x0000000094a691a4 },
+ /* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */
+ { 0x00000001ea910712, 0x00000001271ecdfa },
+ /* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */
+ { 0x0000000167127128, 0x000000009e54475a },
+ /* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */
+ { 0x0000000019e790a2, 0x00000000c9c099ee },
+ /* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */
+ { 0x000000003788f710, 0x000000009a2f736c },
+ /* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */
+ { 0x00000001682a160e, 0x00000000bb9f4996 },
+ /* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */
+ { 0x000000007f0ebd2e, 0x00000001db688050 },
+ /* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */
+ { 0x000000002b032080, 0x00000000e9b10af4 },
+ /* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */
+ { 0x00000000cfd1664a, 0x000000012d4545e4 },
+ /* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */
+ { 0x00000000aa1181c2, 0x000000000361139c },
+ /* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */
+ { 0x00000000ddd08002, 0x00000001a5a1a3a8 },
+ /* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */
+ { 0x00000000e8dd0446, 0x000000006844e0b0 },
+ /* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */
+ { 0x00000001bbd94a00, 0x00000000c3762f28 },
+ /* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */
+ { 0x00000000ab6cd180, 0x00000001d26287a2 },
+ /* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */
+ { 0x0000000031803ce2, 0x00000001f6f0bba8 },
+ /* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */
+ { 0x0000000024f40b0c, 0x000000002ffabd62 },
+ /* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */
+ { 0x00000001ba1d9834, 0x00000000fb4516b8 },
+ /* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */
+ { 0x0000000104de61aa, 0x000000018cfa961c },
+ /* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */
+ { 0x0000000113e40d46, 0x000000019e588d52 },
+ /* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */
+ { 0x00000001415598a0, 0x00000001180f0bbc },
+ /* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */
+ { 0x00000000bf6c8c90, 0x00000000e1d9177a },
+ /* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */
+ { 0x00000001788b0504, 0x0000000105abc27c },
+ /* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */
+ { 0x0000000038385d02, 0x00000000972e4a58 },
+ /* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */
+ { 0x00000001b6c83844, 0x0000000183499a5e },
+ /* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */
+ { 0x0000000051061a8a, 0x00000001c96a8cca },
+ /* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */
+ { 0x000000017351388a, 0x00000001a1a5b60c },
+ /* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */
+ { 0x0000000132928f92, 0x00000000e4b6ac9c },
+ /* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */
+ { 0x00000000e6b4f48a, 0x00000001807e7f5a },
+ /* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */
+ { 0x0000000039d15e90, 0x000000017a7e3bc8 },
+ /* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */
+ { 0x00000000312d6074, 0x00000000d73975da },
+ /* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */
+ { 0x000000017bbb2cc4, 0x000000017375d038 },
+ /* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */
+ { 0x000000016ded3e18, 0x00000000193680bc },
+ /* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */
+ { 0x00000000f1638b16, 0x00000000999b06f6 },
+ /* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */
+ { 0x00000001d38b9ecc, 0x00000001f685d2b8 },
+ /* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */
+ { 0x000000018b8d09dc, 0x00000001f4ecbed2 },
+ /* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */
+ { 0x00000000e7bc27d2, 0x00000000ba16f1a0 },
+ /* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */
+ { 0x00000000275e1e96, 0x0000000115aceac4 },
+ /* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */
+ { 0x00000000e2e3031e, 0x00000001aeff6292 },
+ /* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */
+ { 0x00000001041c84d8, 0x000000009640124c },
+ /* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */
+ { 0x00000000706ce672, 0x0000000114f41f02 },
+ /* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */
+ { 0x000000015d5070da, 0x000000009c5f3586 },
+ /* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */
+ { 0x0000000038f9493a, 0x00000001878275fa },
+ /* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */
+ { 0x00000000a3348a76, 0x00000000ddc42ce8 },
+ /* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */
+ { 0x00000001ad0aab92, 0x0000000181d2c73a },
+ /* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */
+ { 0x000000019e85f712, 0x0000000141c9320a },
+ /* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */
+ { 0x000000005a871e76, 0x000000015235719a },
+ /* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */
+ { 0x000000017249c662, 0x00000000be27d804 },
+ /* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */
+ { 0x000000003a084712, 0x000000006242d45a },
+ /* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */
+ { 0x00000000ed438478, 0x000000009a53638e },
+ /* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */
+ { 0x00000000abac34cc, 0x00000001001ecfb6 },
+ /* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */
+ { 0x000000005f35ef3e, 0x000000016d7c2d64 },
+ /* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */
+ { 0x0000000047d6608c, 0x00000001d0ce46c0 },
+ /* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */
+ { 0x000000002d01470e, 0x0000000124c907b4 },
+ /* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */
+ { 0x0000000158bbc7b0, 0x0000000018a555ca },
+ /* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */
+ { 0x00000000c0a23e8e, 0x000000006b0980bc },
+ /* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */
+ { 0x00000001ebd85c88, 0x000000008bbba964 },
+ /* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */
+ { 0x000000019ee20bb2, 0x00000001070a5a1e },
+ /* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */
+ { 0x00000001acabf2d6, 0x000000002204322a },
+ /* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */
+ { 0x00000001b7963d56, 0x00000000a27524d0 },
+ /* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */
+ { 0x000000017bffa1fe, 0x0000000020b1e4ba },
+ /* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */
+ { 0x000000001f15333e, 0x0000000032cc27fc },
+ /* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */
+ { 0x000000018593129e, 0x0000000044dd22b8 },
+ /* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */
+ { 0x000000019cb32602, 0x00000000dffc9e0a },
+ /* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */
+ { 0x0000000142b05cc8, 0x00000001b7a0ed14 },
+ /* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */
+ { 0x00000001be49e7a4, 0x00000000c7842488 },
+ /* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */
+ { 0x0000000108f69d6c, 0x00000001c02a4fee },
+ /* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */
+ { 0x000000006c0971f0, 0x000000003c273778 },
+ /* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */
+ { 0x000000005b16467a, 0x00000001d63f8894 },
+ /* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */
+ { 0x00000001551a628e, 0x000000006be557d6 },
+ /* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */
+ { 0x000000019e42ea92, 0x000000006a7806ea },
+ /* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */
+ { 0x000000012fa83ff2, 0x000000016155aa0c },
+ /* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */
+ { 0x000000011ca9cde0, 0x00000000908650ac },
+ /* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */
+ { 0x00000000c8e5cd74, 0x00000000aa5a8084 },
+ /* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */
+ { 0x0000000096c27f0c, 0x0000000191bb500a },
+ /* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */
+ { 0x000000002baed926, 0x0000000064e9bed0 },
+ /* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */
+ { 0x000000017c8de8d2, 0x000000009444f302 },
+ /* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */
+ { 0x00000000d43d6068, 0x000000019db07d3c },
+ /* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */
+ { 0x00000000cb2c4b26, 0x00000001359e3e6e },
+ /* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */
+ { 0x0000000145b8da26, 0x00000001e4f10dd2 },
+ /* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */
+ { 0x000000018fff4b08, 0x0000000124f5735e },
+ /* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */
+ { 0x0000000150b58ed0, 0x0000000124760a4c },
+ /* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */
+ { 0x00000001549f39bc, 0x000000000f1fc186 },
+ /* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */
+ { 0x00000000ef4d2f42, 0x00000000150e4cc4 },
+ /* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */
+ { 0x00000001b1468572, 0x000000002a6204e8 },
+ /* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */
+ { 0x000000013d7403b2, 0x00000000beb1d432 },
+ /* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */
+ { 0x00000001a4681842, 0x0000000135f3f1f0 },
+ /* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */
+ { 0x0000000167714492, 0x0000000074fe2232 },
+ /* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */
+ { 0x00000001e599099a, 0x000000001ac6e2ba },
+ /* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */
+ { 0x00000000fe128194, 0x0000000013fca91e },
+ /* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */
+ { 0x0000000077e8b990, 0x0000000183f4931e },
+ /* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */
+ { 0x00000001a267f63a, 0x00000000b6d9b4e4 },
+ /* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */
+ { 0x00000001945c245a, 0x00000000b5188656 },
+ /* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */
+ { 0x0000000149002e76, 0x0000000027a81a84 },
+ /* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */
+ { 0x00000001bb8310a4, 0x0000000125699258 },
+ /* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */
+ { 0x000000019ec60bcc, 0x00000001b23de796 },
+ /* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */
+ { 0x000000012d8590ae, 0x00000000fe4365dc },
+ /* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */
+ { 0x0000000065b00684, 0x00000000c68f497a },
+ /* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */
+ { 0x000000015e5aeadc, 0x00000000fbf521ee },
+ /* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */
+ { 0x00000000b77ff2b0, 0x000000015eac3378 },
+ /* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */
+ { 0x0000000188da2ff6, 0x0000000134914b90 },
+ /* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */
+ { 0x0000000063da929a, 0x0000000016335cfe },
+ /* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */
+ { 0x00000001389caa80, 0x000000010372d10c },
+ /* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */
+ { 0x000000013db599d2, 0x000000015097b908 },
+ /* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */
+ { 0x0000000122505a86, 0x00000001227a7572 },
+ /* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */
+ { 0x000000016bd72746, 0x000000009a8f75c0 },
+ /* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */
+ { 0x00000001c3faf1d4, 0x00000000682c77a2 },
+ /* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */
+ { 0x00000001111c826c, 0x00000000231f091c },
+ /* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */
+ { 0x00000000153e9fb2, 0x000000007d4439f2 },
+ /* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */
+ { 0x000000002b1f7b60, 0x000000017e221efc },
+ /* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */
+ { 0x00000000b1dba570, 0x0000000167457c38 },
+ /* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */
+ { 0x00000001f6397b76, 0x00000000bdf081c4 },
+ /* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */
+ { 0x0000000156335214, 0x000000016286d6b0 },
+ /* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */
+ { 0x00000001d70e3986, 0x00000000c84f001c },
+ /* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */
+ { 0x000000003701a774, 0x0000000064efe7c0 },
+ /* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */
+ { 0x00000000ac81ef72, 0x000000000ac2d904 },
+ /* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */
+ { 0x0000000133212464, 0x00000000fd226d14 },
+ /* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */
+ { 0x00000000e4e45610, 0x000000011cfd42e0 },
+ /* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */
+ { 0x000000000c1bd370, 0x000000016e5a5678 },
+ /* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */
+ { 0x00000001a7b9e7a6, 0x00000001d888fe22 },
+ /* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */
+ { 0x000000007d657a10, 0x00000001af77fcd4 }
+#else /* __LITTLE_ENDIAN__ */
+ /* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */
+ { 0x00000001651797d2, 0x0000000099ea94a8 },
+ /* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */
+ { 0x0000000021e0d56c, 0x00000000945a8420 },
+ /* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */
+ { 0x000000000f95ecaa, 0x0000000030762706 },
+ /* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */
+ { 0x00000001ebd224ac, 0x00000001a52fc582 },
+ /* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */
+ { 0x000000000ccb97ca, 0x00000001a4a7167a },
+ /* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */
+ { 0x00000001006ec8a8, 0x000000000c18249a },
+ /* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */
+ { 0x000000014f58f196, 0x00000000a924ae7c },
+ /* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */
+ { 0x00000001a7192ca6, 0x00000001e12ccc12 },
+ /* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */
+ { 0x000000019a64bab2, 0x00000000a0b9d4ac },
+ /* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */
+ { 0x0000000014f4ed2e, 0x0000000095e8ddfe },
+ /* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */
+ { 0x000000011092b6a2, 0x00000000233fddc4 },
+ /* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */
+ { 0x00000000c8a1629c, 0x00000001b4529b62 },
+ /* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */
+ { 0x000000017bf32e8e, 0x00000001a7fa0e64 },
+ /* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */
+ { 0x00000001f8cc6582, 0x00000001b5334592 },
+ /* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */
+ { 0x000000008631ddf0, 0x000000011f8ee1b4 },
+ /* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */
+ { 0x000000007e5a76d0, 0x000000006252e632 },
+ /* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */
+ { 0x000000002b09b31c, 0x00000000ab973e84 },
+ /* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */
+ { 0x00000001b2df1f84, 0x000000007734f5ec },
+ /* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */
+ { 0x00000001d6f56afc, 0x000000007c547798 },
+ /* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */
+ { 0x00000001b9b5e70c, 0x000000007ec40210 },
+ /* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */
+ { 0x0000000034b626d2, 0x00000001ab1695a8 },
+ /* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */
+ { 0x000000014c53479a, 0x0000000090494bba },
+ /* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */
+ { 0x00000001a6d179a4, 0x00000001123fb816 },
+ /* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */
+ { 0x000000015abd16b4, 0x00000001e188c74c },
+ /* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */
+ { 0x00000000018f9852, 0x00000001c2d3451c },
+ /* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */
+ { 0x000000001fb3084a, 0x00000000f55cf1ca },
+ /* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */
+ { 0x00000000c53dfb04, 0x00000001a0531540 },
+ /* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */
+ { 0x00000000e10c9ad6, 0x0000000132cd7ebc },
+ /* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */
+ { 0x0000000025aa994a, 0x0000000073ab7f36 },
+ /* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */
+ { 0x00000000fa3a74c4, 0x0000000041aed1c2 },
+ /* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */
+ { 0x0000000033eb3f40, 0x0000000136c53800 },
+ /* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */
+ { 0x000000017193f296, 0x0000000126835a30 },
+ /* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */
+ { 0x0000000043f6c86a, 0x000000006241b502 },
+ /* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */
+ { 0x000000016b513ec6, 0x00000000d5196ad4 },
+ /* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */
+ { 0x00000000c8f25b4e, 0x000000009cfa769a },
+ /* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */
+ { 0x00000001a45048ec, 0x00000000920e5df4 },
+ /* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */
+ { 0x000000000c441004, 0x0000000169dc310e },
+ /* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */
+ { 0x000000000e17cad6, 0x0000000009fc331c },
+ /* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */
+ { 0x00000001253ae964, 0x000000010d94a81e },
+ /* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */
+ { 0x00000001d7c88ebc, 0x0000000027a20ab2 },
+ /* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */
+ { 0x00000001e7ca913a, 0x0000000114f87504 },
+ /* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */
+ { 0x0000000033ed078a, 0x000000004b076d96 },
+ /* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */
+ { 0x00000000e1839c78, 0x00000000da4d1e74 },
+ /* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */
+ { 0x00000001322b267e, 0x000000001b81f672 },
+ /* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */
+ { 0x00000000638231b6, 0x000000009367c988 },
+ /* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */
+ { 0x00000001ee7f16f4, 0x00000001717214ca },
+ /* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */
+ { 0x0000000117d9924a, 0x000000009f47d820 },
+ /* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */
+ { 0x00000000e1a9e0c4, 0x000000010d9a47d2 },
+ /* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */
+ { 0x00000001403731dc, 0x00000000a696c58c },
+ /* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */
+ { 0x00000001a5ea9682, 0x000000002aa28ec6 },
+ /* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */
+ { 0x0000000101c5c578, 0x00000001fe18fd9a },
+ /* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */
+ { 0x00000000dddf6494, 0x000000019d4fc1ae },
+ /* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */
+ { 0x00000000f1c3db28, 0x00000001ba0e3dea },
+ /* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */
+ { 0x000000013112fb9c, 0x0000000074b59a5e },
+ /* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */
+ { 0x00000000b680b906, 0x00000000f2b5ea98 },
+ /* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */
+ { 0x000000001a282932, 0x0000000187132676 },
+ /* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */
+ { 0x0000000089406e7e, 0x000000010a8c6ad4 },
+ /* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */
+ { 0x00000001def6be8c, 0x00000001e21dfe70 },
+ /* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */
+ { 0x0000000075258728, 0x00000001da0050e4 },
+ /* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */
+ { 0x000000019536090a, 0x00000000772172ae },
+ /* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */
+ { 0x00000000f2455bfc, 0x00000000e47724aa },
+ /* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */
+ { 0x000000018c40baf4, 0x000000003cd63ac4 },
+ /* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */
+ { 0x000000004cd390d4, 0x00000001bf47d352 },
+ /* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */
+ { 0x00000001e4ece95a, 0x000000018dc1d708 },
+ /* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */
+ { 0x000000001a3ee918, 0x000000002d4620a4 },
+ /* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */
+ { 0x000000007c652fb8, 0x0000000058fd1740 },
+ /* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */
+ { 0x000000011c67842c, 0x00000000dadd9bfc },
+ /* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */
+ { 0x00000000254f759c, 0x00000001ea2140be },
+ /* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */
+ { 0x000000007ece94ca, 0x000000009de128ba },
+ /* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */
+ { 0x0000000038f258c2, 0x000000013ac3aa8e },
+ /* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */
+ { 0x00000001cdf17b00, 0x0000000099980562 },
+ /* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */
+ { 0x000000011f882c16, 0x00000001c1579c86 },
+ /* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */
+ { 0x0000000100093fc8, 0x0000000068dbbf94 },
+ /* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */
+ { 0x00000001cd684f16, 0x000000004509fb04 },
+ /* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */
+ { 0x000000004bc6a70a, 0x00000001202f6398 },
+ /* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */
+ { 0x000000004fc7e8e4, 0x000000013aea243e },
+ /* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */
+ { 0x0000000130103f1c, 0x00000001b4052ae6 },
+ /* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */
+ { 0x0000000111b0024c, 0x00000001cd2a0ae8 },
+ /* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */
+ { 0x000000010b3079da, 0x00000001fe4aa8b4 },
+ /* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */
+ { 0x000000010192bcc2, 0x00000001d1559a42 },
+ /* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */
+ { 0x0000000074838d50, 0x00000001f3e05ecc },
+ /* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */
+ { 0x000000001b20f520, 0x0000000104ddd2cc },
+ /* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */
+ { 0x0000000050c3590a, 0x000000015393153c },
+ /* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */
+ { 0x00000000b41cac8e, 0x0000000057e942c6 },
+ /* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */
+ { 0x000000000c72cc78, 0x000000012c633850 },
+ /* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */
+ { 0x0000000030cdb032, 0x00000000ebcaae4c },
+ /* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */
+ { 0x000000013e09fc32, 0x000000013ee532a6 },
+ /* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */
+ { 0x000000001ed624d2, 0x00000001bf0cbc7e },
+ /* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */
+ { 0x00000000781aee1a, 0x00000000d50b7a5a },
+ /* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */
+ { 0x00000001c4d8348c, 0x0000000002fca6e8 },
+ /* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */
+ { 0x0000000057a40336, 0x000000007af40044 },
+ /* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */
+ { 0x0000000085544940, 0x0000000016178744 },
+ /* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */
+ { 0x000000019cd21e80, 0x000000014c177458 },
+ /* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */
+ { 0x000000013eb95bc0, 0x000000011b6ddf04 },
+ /* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */
+ { 0x00000001dfc9fdfc, 0x00000001f3e29ccc },
+ /* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */
+ { 0x00000000cd028bc2, 0x0000000135ae7562 },
+ /* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */
+ { 0x0000000090db8c44, 0x0000000190ef812c },
+ /* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */
+ { 0x000000010010a4ce, 0x0000000067a2c786 },
+ /* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */
+ { 0x00000001c8f4c72c, 0x0000000048b9496c },
+ /* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */
+ { 0x000000001c26170c, 0x000000015a422de6 },
+ /* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */
+ { 0x00000000e3fccf68, 0x00000001ef0e3640 },
+ /* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */
+ { 0x00000000d513ed24, 0x00000001006d2d26 },
+ /* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */
+ { 0x00000000141beada, 0x00000001170d56d6 },
+ /* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */
+ { 0x000000011071aea0, 0x00000000a5fb613c },
+ /* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */
+ { 0x000000012e19080a, 0x0000000040bbf7fc },
+ /* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */
+ { 0x0000000100ecf826, 0x000000016ac3a5b2 },
+ /* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */
+ { 0x0000000069b09412, 0x00000000abf16230 },
+ /* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */
+ { 0x0000000122297bac, 0x00000001ebe23fac },
+ /* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */
+ { 0x00000000e9e4b068, 0x000000008b6a0894 },
+ /* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */
+ { 0x000000004b38651a, 0x00000001288ea478 },
+ /* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */
+ { 0x00000001468360e2, 0x000000016619c442 },
+ /* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */
+ { 0x00000000121c2408, 0x0000000086230038 },
+ /* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */
+ { 0x00000000da7e7d08, 0x000000017746a756 },
+ /* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */
+ { 0x00000001058d7652, 0x0000000191b8f8f8 },
+ /* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */
+ { 0x000000014a098a90, 0x000000008e167708 },
+ /* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */
+ { 0x0000000020dbe72e, 0x0000000148b22d54 },
+ /* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */
+ { 0x000000011e7323e8, 0x0000000044ba2c3c },
+ /* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */
+ { 0x00000000d5d4bf94, 0x00000000b54d2b52 },
+ /* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */
+ { 0x0000000199d8746c, 0x0000000005a4fd8a },
+ /* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */
+ { 0x00000000ce9ca8a0, 0x0000000139f9fc46 },
+ /* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */
+ { 0x00000000136edece, 0x000000015a1fa824 },
+ /* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */
+ { 0x000000019b92a068, 0x000000000a61ae4c },
+ /* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */
+ { 0x0000000071d62206, 0x0000000145e9113e },
+ /* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */
+ { 0x00000000dfc50158, 0x000000006a348448 },
+ /* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */
+ { 0x00000001517626bc, 0x000000004d80a08c },
+ /* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */
+ { 0x0000000148d1e4fa, 0x000000014b6837a0 },
+ /* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */
+ { 0x0000000094d8266e, 0x000000016896a7fc },
+ /* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */
+ { 0x00000000606c5e34, 0x000000014f187140 },
+ /* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */
+ { 0x000000019766beaa, 0x000000019581b9da },
+ /* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */
+ { 0x00000001d80c506c, 0x00000001091bc984 },
+ /* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */
+ { 0x000000001e73837c, 0x000000001067223c },
+ /* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */
+ { 0x0000000064d587de, 0x00000001ab16ea02 },
+ /* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */
+ { 0x00000000f4a507b0, 0x000000013c4598a8 },
+ /* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */
+ { 0x0000000040e342fc, 0x00000000b3735430 },
+ /* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */
+ { 0x00000001d5ad9c3a, 0x00000001bb3fc0c0 },
+ /* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */
+ { 0x0000000094a691a4, 0x00000001570ae19c },
+ /* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */
+ { 0x00000001271ecdfa, 0x00000001ea910712 },
+ /* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */
+ { 0x000000009e54475a, 0x0000000167127128 },
+ /* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */
+ { 0x00000000c9c099ee, 0x0000000019e790a2 },
+ /* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */
+ { 0x000000009a2f736c, 0x000000003788f710 },
+ /* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */
+ { 0x00000000bb9f4996, 0x00000001682a160e },
+ /* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */
+ { 0x00000001db688050, 0x000000007f0ebd2e },
+ /* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */
+ { 0x00000000e9b10af4, 0x000000002b032080 },
+ /* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */
+ { 0x000000012d4545e4, 0x00000000cfd1664a },
+ /* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */
+ { 0x000000000361139c, 0x00000000aa1181c2 },
+ /* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */
+ { 0x00000001a5a1a3a8, 0x00000000ddd08002 },
+ /* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */
+ { 0x000000006844e0b0, 0x00000000e8dd0446 },
+ /* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */
+ { 0x00000000c3762f28, 0x00000001bbd94a00 },
+ /* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */
+ { 0x00000001d26287a2, 0x00000000ab6cd180 },
+ /* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */
+ { 0x00000001f6f0bba8, 0x0000000031803ce2 },
+ /* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */
+ { 0x000000002ffabd62, 0x0000000024f40b0c },
+ /* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */
+ { 0x00000000fb4516b8, 0x00000001ba1d9834 },
+ /* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */
+ { 0x000000018cfa961c, 0x0000000104de61aa },
+ /* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */
+ { 0x000000019e588d52, 0x0000000113e40d46 },
+ /* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */
+ { 0x00000001180f0bbc, 0x00000001415598a0 },
+ /* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */
+ { 0x00000000e1d9177a, 0x00000000bf6c8c90 },
+ /* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */
+ { 0x0000000105abc27c, 0x00000001788b0504 },
+ /* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */
+ { 0x00000000972e4a58, 0x0000000038385d02 },
+ /* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */
+ { 0x0000000183499a5e, 0x00000001b6c83844 },
+ /* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */
+ { 0x00000001c96a8cca, 0x0000000051061a8a },
+ /* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */
+ { 0x00000001a1a5b60c, 0x000000017351388a },
+ /* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */
+ { 0x00000000e4b6ac9c, 0x0000000132928f92 },
+ /* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */
+ { 0x00000001807e7f5a, 0x00000000e6b4f48a },
+ /* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */
+ { 0x000000017a7e3bc8, 0x0000000039d15e90 },
+ /* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */
+ { 0x00000000d73975da, 0x00000000312d6074 },
+ /* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */
+ { 0x000000017375d038, 0x000000017bbb2cc4 },
+ /* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */
+ { 0x00000000193680bc, 0x000000016ded3e18 },
+ /* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */
+ { 0x00000000999b06f6, 0x00000000f1638b16 },
+ /* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */
+ { 0x00000001f685d2b8, 0x00000001d38b9ecc },
+ /* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */
+ { 0x00000001f4ecbed2, 0x000000018b8d09dc },
+ /* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */
+ { 0x00000000ba16f1a0, 0x00000000e7bc27d2 },
+ /* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */
+ { 0x0000000115aceac4, 0x00000000275e1e96 },
+ /* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */
+ { 0x00000001aeff6292, 0x00000000e2e3031e },
+ /* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */
+ { 0x000000009640124c, 0x00000001041c84d8 },
+ /* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */
+ { 0x0000000114f41f02, 0x00000000706ce672 },
+ /* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */
+ { 0x000000009c5f3586, 0x000000015d5070da },
+ /* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */
+ { 0x00000001878275fa, 0x0000000038f9493a },
+ /* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */
+ { 0x00000000ddc42ce8, 0x00000000a3348a76 },
+ /* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */
+ { 0x0000000181d2c73a, 0x00000001ad0aab92 },
+ /* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */
+ { 0x0000000141c9320a, 0x000000019e85f712 },
+ /* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */
+ { 0x000000015235719a, 0x000000005a871e76 },
+ /* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */
+ { 0x00000000be27d804, 0x000000017249c662 },
+ /* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */
+ { 0x000000006242d45a, 0x000000003a084712 },
+ /* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */
+ { 0x000000009a53638e, 0x00000000ed438478 },
+ /* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */
+ { 0x00000001001ecfb6, 0x00000000abac34cc },
+ /* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */
+ { 0x000000016d7c2d64, 0x000000005f35ef3e },
+ /* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */
+ { 0x00000001d0ce46c0, 0x0000000047d6608c },
+ /* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */
+ { 0x0000000124c907b4, 0x000000002d01470e },
+ /* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */
+ { 0x0000000018a555ca, 0x0000000158bbc7b0 },
+ /* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */
+ { 0x000000006b0980bc, 0x00000000c0a23e8e },
+ /* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */
+ { 0x000000008bbba964, 0x00000001ebd85c88 },
+ /* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */
+ { 0x00000001070a5a1e, 0x000000019ee20bb2 },
+ /* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */
+ { 0x000000002204322a, 0x00000001acabf2d6 },
+ /* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */
+ { 0x00000000a27524d0, 0x00000001b7963d56 },
+ /* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */
+ { 0x0000000020b1e4ba, 0x000000017bffa1fe },
+ /* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */
+ { 0x0000000032cc27fc, 0x000000001f15333e },
+ /* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */
+ { 0x0000000044dd22b8, 0x000000018593129e },
+ /* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */
+ { 0x00000000dffc9e0a, 0x000000019cb32602 },
+ /* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */
+ { 0x00000001b7a0ed14, 0x0000000142b05cc8 },
+ /* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */
+ { 0x00000000c7842488, 0x00000001be49e7a4 },
+ /* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */
+ { 0x00000001c02a4fee, 0x0000000108f69d6c },
+ /* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */
+ { 0x000000003c273778, 0x000000006c0971f0 },
+ /* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */
+ { 0x00000001d63f8894, 0x000000005b16467a },
+ /* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */
+ { 0x000000006be557d6, 0x00000001551a628e },
+ /* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */
+ { 0x000000006a7806ea, 0x000000019e42ea92 },
+ /* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */
+ { 0x000000016155aa0c, 0x000000012fa83ff2 },
+ /* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */
+ { 0x00000000908650ac, 0x000000011ca9cde0 },
+ /* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */
+ { 0x00000000aa5a8084, 0x00000000c8e5cd74 },
+ /* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */
+ { 0x0000000191bb500a, 0x0000000096c27f0c },
+ /* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */
+ { 0x0000000064e9bed0, 0x000000002baed926 },
+ /* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */
+ { 0x000000009444f302, 0x000000017c8de8d2 },
+ /* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */
+ { 0x000000019db07d3c, 0x00000000d43d6068 },
+ /* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */
+ { 0x00000001359e3e6e, 0x00000000cb2c4b26 },
+ /* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */
+ { 0x00000001e4f10dd2, 0x0000000145b8da26 },
+ /* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */
+ { 0x0000000124f5735e, 0x000000018fff4b08 },
+ /* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */
+ { 0x0000000124760a4c, 0x0000000150b58ed0 },
+ /* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */
+ { 0x000000000f1fc186, 0x00000001549f39bc },
+ /* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */
+ { 0x00000000150e4cc4, 0x00000000ef4d2f42 },
+ /* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */
+ { 0x000000002a6204e8, 0x00000001b1468572 },
+ /* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */
+ { 0x00000000beb1d432, 0x000000013d7403b2 },
+ /* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */
+ { 0x0000000135f3f1f0, 0x00000001a4681842 },
+ /* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */
+ { 0x0000000074fe2232, 0x0000000167714492 },
+ /* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */
+ { 0x000000001ac6e2ba, 0x00000001e599099a },
+ /* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */
+ { 0x0000000013fca91e, 0x00000000fe128194 },
+ /* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */
+ { 0x0000000183f4931e, 0x0000000077e8b990 },
+ /* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */
+ { 0x00000000b6d9b4e4, 0x00000001a267f63a },
+ /* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */
+ { 0x00000000b5188656, 0x00000001945c245a },
+ /* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */
+ { 0x0000000027a81a84, 0x0000000149002e76 },
+ /* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */
+ { 0x0000000125699258, 0x00000001bb8310a4 },
+ /* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */
+ { 0x00000001b23de796, 0x000000019ec60bcc },
+ /* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */
+ { 0x00000000fe4365dc, 0x000000012d8590ae },
+ /* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */
+ { 0x00000000c68f497a, 0x0000000065b00684 },
+ /* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */
+ { 0x00000000fbf521ee, 0x000000015e5aeadc },
+ /* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */
+ { 0x000000015eac3378, 0x00000000b77ff2b0 },
+ /* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */
+ { 0x0000000134914b90, 0x0000000188da2ff6 },
+ /* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */
+ { 0x0000000016335cfe, 0x0000000063da929a },
+ /* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */
+ { 0x000000010372d10c, 0x00000001389caa80 },
+ /* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */
+ { 0x000000015097b908, 0x000000013db599d2 },
+ /* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */
+ { 0x00000001227a7572, 0x0000000122505a86 },
+ /* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */
+ { 0x000000009a8f75c0, 0x000000016bd72746 },
+ /* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */
+ { 0x00000000682c77a2, 0x00000001c3faf1d4 },
+ /* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */
+ { 0x00000000231f091c, 0x00000001111c826c },
+ /* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */
+ { 0x000000007d4439f2, 0x00000000153e9fb2 },
+ /* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */
+ { 0x000000017e221efc, 0x000000002b1f7b60 },
+ /* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */
+ { 0x0000000167457c38, 0x00000000b1dba570 },
+ /* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */
+ { 0x00000000bdf081c4, 0x00000001f6397b76 },
+ /* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */
+ { 0x000000016286d6b0, 0x0000000156335214 },
+ /* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */
+ { 0x00000000c84f001c, 0x00000001d70e3986 },
+ /* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */
+ { 0x0000000064efe7c0, 0x000000003701a774 },
+ /* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */
+ { 0x000000000ac2d904, 0x00000000ac81ef72 },
+ /* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */
+ { 0x00000000fd226d14, 0x0000000133212464 },
+ /* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */
+ { 0x000000011cfd42e0, 0x00000000e4e45610 },
+ /* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */
+ { 0x000000016e5a5678, 0x000000000c1bd370 },
+ /* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */
+ { 0x00000001d888fe22, 0x00000001a7b9e7a6 },
+ /* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */
+ { 0x00000001af77fcd4, 0x000000007d657a10 }
+#endif /* __LITTLE_ENDIAN__ */
+ };
+
+/* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */
+
+static const __vector unsigned long long vcrc_short_const[16]
+ __attribute__((aligned (16))) = {
+#ifdef __LITTLE_ENDIAN__
+ /* x^1952 mod p(x) , x^1984 mod p(x) , x^2016 mod p(x) , x^2048 mod p(x) */
+ { 0x99168a18ec447f11, 0xed837b2613e8221e },
+ /* x^1824 mod p(x) , x^1856 mod p(x) , x^1888 mod p(x) , x^1920 mod p(x) */
+ { 0xe23e954e8fd2cd3c, 0xc8acdd8147b9ce5a },
+ /* x^1696 mod p(x) , x^1728 mod p(x) , x^1760 mod p(x) , x^1792 mod p(x) */
+ { 0x92f8befe6b1d2b53, 0xd9ad6d87d4277e25 },
+ /* x^1568 mod p(x) , x^1600 mod p(x) , x^1632 mod p(x) , x^1664 mod p(x) */
+ { 0xf38a3556291ea462, 0xc10ec5e033fbca3b },
+ /* x^1440 mod p(x) , x^1472 mod p(x) , x^1504 mod p(x) , x^1536 mod p(x) */
+ { 0x974ac56262b6ca4b, 0xc0b55b0e82e02e2f },
+ /* x^1312 mod p(x) , x^1344 mod p(x) , x^1376 mod p(x) , x^1408 mod p(x) */
+ { 0x855712b3784d2a56, 0x71aa1df0e172334d },
+ /* x^1184 mod p(x) , x^1216 mod p(x) , x^1248 mod p(x) , x^1280 mod p(x) */
+ { 0xa5abe9f80eaee722, 0xfee3053e3969324d },
+ /* x^1056 mod p(x) , x^1088 mod p(x) , x^1120 mod p(x) , x^1152 mod p(x) */
+ { 0x1fa0943ddb54814c, 0xf44779b93eb2bd08 },
+ /* x^928 mod p(x) , x^960 mod p(x) , x^992 mod p(x) , x^1024 mod p(x) */
+ { 0xa53ff440d7bbfe6a, 0xf5449b3f00cc3374 },
+ /* x^800 mod p(x) , x^832 mod p(x) , x^864 mod p(x) , x^896 mod p(x) */
+ { 0xebe7e3566325605c, 0x6f8346e1d777606e },
+ /* x^672 mod p(x) , x^704 mod p(x) , x^736 mod p(x) , x^768 mod p(x) */
+ { 0xc65a272ce5b592b8, 0xe3ab4f2ac0b95347 },
+ /* x^544 mod p(x) , x^576 mod p(x) , x^608 mod p(x) , x^640 mod p(x) */
+ { 0x5705a9ca4721589f, 0xaa2215ea329ecc11 },
+ /* x^416 mod p(x) , x^448 mod p(x) , x^480 mod p(x) , x^512 mod p(x) */
+ { 0xe3720acb88d14467, 0x1ed8f66ed95efd26 },
+ /* x^288 mod p(x) , x^320 mod p(x) , x^352 mod p(x) , x^384 mod p(x) */
+ { 0xba1aca0315141c31, 0x78ed02d5a700e96a },
+ /* x^160 mod p(x) , x^192 mod p(x) , x^224 mod p(x) , x^256 mod p(x) */
+ { 0xad2a31b3ed627dae, 0xba8ccbe832b39da3 },
+ /* x^32 mod p(x) , x^64 mod p(x) , x^96 mod p(x) , x^128 mod p(x) */
+ { 0x6655004fa06a2517, 0xedb88320b1e6b092 }
+#else /* __LITTLE_ENDIAN__ */
+ /* x^1952 mod p(x) , x^1984 mod p(x) , x^2016 mod p(x) , x^2048 mod p(x) */
+ { 0xed837b2613e8221e, 0x99168a18ec447f11 },
+ /* x^1824 mod p(x) , x^1856 mod p(x) , x^1888 mod p(x) , x^1920 mod p(x) */
+ { 0xc8acdd8147b9ce5a, 0xe23e954e8fd2cd3c },
+ /* x^1696 mod p(x) , x^1728 mod p(x) , x^1760 mod p(x) , x^1792 mod p(x) */
+ { 0xd9ad6d87d4277e25, 0x92f8befe6b1d2b53 },
+ /* x^1568 mod p(x) , x^1600 mod p(x) , x^1632 mod p(x) , x^1664 mod p(x) */
+ { 0xc10ec5e033fbca3b, 0xf38a3556291ea462 },
+ /* x^1440 mod p(x) , x^1472 mod p(x) , x^1504 mod p(x) , x^1536 mod p(x) */
+ { 0xc0b55b0e82e02e2f, 0x974ac56262b6ca4b },
+ /* x^1312 mod p(x) , x^1344 mod p(x) , x^1376 mod p(x) , x^1408 mod p(x) */
+ { 0x71aa1df0e172334d, 0x855712b3784d2a56 },
+ /* x^1184 mod p(x) , x^1216 mod p(x) , x^1248 mod p(x) , x^1280 mod p(x) */
+ { 0xfee3053e3969324d, 0xa5abe9f80eaee722 },
+ /* x^1056 mod p(x) , x^1088 mod p(x) , x^1120 mod p(x) , x^1152 mod p(x) */
+ { 0xf44779b93eb2bd08, 0x1fa0943ddb54814c },
+ /* x^928 mod p(x) , x^960 mod p(x) , x^992 mod p(x) , x^1024 mod p(x) */
+ { 0xf5449b3f00cc3374, 0xa53ff440d7bbfe6a },
+ /* x^800 mod p(x) , x^832 mod p(x) , x^864 mod p(x) , x^896 mod p(x) */
+ { 0x6f8346e1d777606e, 0xebe7e3566325605c },
+ /* x^672 mod p(x) , x^704 mod p(x) , x^736 mod p(x) , x^768 mod p(x) */
+ { 0xe3ab4f2ac0b95347, 0xc65a272ce5b592b8 },
+ /* x^544 mod p(x) , x^576 mod p(x) , x^608 mod p(x) , x^640 mod p(x) */
+ { 0xaa2215ea329ecc11, 0x5705a9ca4721589f },
+ /* x^416 mod p(x) , x^448 mod p(x) , x^480 mod p(x) , x^512 mod p(x) */
+ { 0x1ed8f66ed95efd26, 0xe3720acb88d14467 },
+ /* x^288 mod p(x) , x^320 mod p(x) , x^352 mod p(x) , x^384 mod p(x) */
+ { 0x78ed02d5a700e96a, 0xba1aca0315141c31 },
+ /* x^160 mod p(x) , x^192 mod p(x) , x^224 mod p(x) , x^256 mod p(x) */
+ { 0xba8ccbe832b39da3, 0xad2a31b3ed627dae },
+ /* x^32 mod p(x) , x^64 mod p(x) , x^96 mod p(x) , x^128 mod p(x) */
+ { 0xedb88320b1e6b092, 0x6655004fa06a2517 }
+#endif /* __LITTLE_ENDIAN__ */
+ };
+
+/* Barrett constants */
+/* 33 bit reflected Barrett constant m - (4^32)/n */
+
+static const __vector unsigned long long v_Barrett_const[2]
+ __attribute__((aligned (16))) = {
+ /* x^64 div p(x) */
+#ifdef __LITTLE_ENDIAN__
+ { 0x00000001f7011641, 0x0000000000000000 },
+ { 0x00000001db710641, 0x0000000000000000 }
+#else /* __LITTLE_ENDIAN__ */
+ { 0x0000000000000000, 0x00000001f7011641 },
+ { 0x0000000000000000, 0x00000001db710641 }
+#endif /* __LITTLE_ENDIAN__ */
+ };
+#endif /* POWER8_INTRINSICS */
+
+#endif /* __ASSEMBLER__ */
diff --git a/contrib/power/crc32_z_power8.c b/contrib/power/crc32_z_power8.c
new file mode 100644
index 0000000..7858cfe
--- /dev/null
+++ b/contrib/power/crc32_z_power8.c
@@ -0,0 +1,679 @@
+/*
+ * Calculate the checksum of data that is 16 byte aligned and a multiple of
+ * 16 bytes.
+ *
+ * The first step is to reduce it to 1024 bits. We do this in 8 parallel
+ * chunks in order to mask the latency of the vpmsum instructions. If we
+ * have more than 32 kB of data to checksum we repeat this step multiple
+ * times, passing in the previous 1024 bits.
+ *
+ * The next step is to reduce the 1024 bits to 64 bits. This step adds
+ * 32 bits of 0s to the end - this matches what a CRC does. We just
+ * calculate constants that land the data in this 32 bits.
+ *
+ * We then use fixed point Barrett reduction to compute a mod n over GF(2)
+ * for n = CRC using POWER8 instructions. We use x = 32.
+ *
+ * http://en.wikipedia.org/wiki/Barrett_reduction
+ *
+ * This code uses gcc vector builtins instead using assembly directly.
+ *
+ * Copyright (C) 2017 Rogerio Alves <rogealve@br.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of either:
+ *
+ * a) the GNU General Public License as published by the Free Software
+ * Foundation; either version 2 of the License, or (at your option)
+ * any later version, or
+ * b) the Apache License, Version 2.0
+ */
+
+#include <altivec.h>
+#include "../../zutil.h"
+#include "power.h"
+
+#define POWER8_INTRINSICS
+#define CRC_TABLE
+
+#ifdef CRC32_CONSTANTS_HEADER
+#include CRC32_CONSTANTS_HEADER
+#else
+#include "crc32_constants.h"
+#endif
+
+#define VMX_ALIGN 16
+#define VMX_ALIGN_MASK (VMX_ALIGN-1)
+
+#ifdef REFLECT
+static unsigned int crc32_align(unsigned int crc, const unsigned char *p,
+ unsigned long len)
+{
+ while (len--)
+ crc = crc_table[(crc ^ *p++) & 0xff] ^ (crc >> 8);
+ return crc;
+}
+#else
+static unsigned int crc32_align(unsigned int crc, const unsigned char *p,
+ unsigned long len)
+{
+ while (len--)
+ crc = crc_table[((crc >> 24) ^ *p++) & 0xff] ^ (crc << 8);
+ return crc;
+}
+#endif
+
+static unsigned int __attribute__ ((aligned (32)))
+__crc32_vpmsum(unsigned int crc, const void* p, unsigned long len);
+
+unsigned long ZLIB_INTERNAL _crc32_z_power8(uLong _crc, const Bytef *_p,
+ z_size_t _len)
+{
+ unsigned int prealign;
+ unsigned int tail;
+
+ /* Map zlib API to crc32_vpmsum API */
+ unsigned int crc = (unsigned int) (0xffffffff & _crc);
+ const unsigned char *p = _p;
+ unsigned long len = (unsigned long) _len;
+
+ if (p == (const unsigned char *) 0x0) return 0;
+#ifdef CRC_XOR
+ crc ^= 0xffffffff;
+#endif
+
+ if (len < VMX_ALIGN + VMX_ALIGN_MASK) {
+ crc = crc32_align(crc, p, len);
+ goto out;
+ }
+
+ if ((unsigned long)p & VMX_ALIGN_MASK) {
+ prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
+ crc = crc32_align(crc, p, prealign);
+ len -= prealign;
+ p += prealign;
+ }
+
+ crc = __crc32_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+
+ tail = len & VMX_ALIGN_MASK;
+ if (tail) {
+ p += len & ~VMX_ALIGN_MASK;
+ crc = crc32_align(crc, p, tail);
+ }
+
+out:
+#ifdef CRC_XOR
+ crc ^= 0xffffffff;
+#endif
+
+ /* Convert to zlib API */
+ return (unsigned long) crc;
+}
+
+#if defined (__clang__)
+#include "clang_workaround.h"
+#else
+#define __builtin_pack_vector(a, b) __builtin_pack_vector_int128 ((a), (b))
+#define __builtin_unpack_vector_0(a) __builtin_unpack_vector_int128 ((vector __int128_t)(a), 0)
+#define __builtin_unpack_vector_1(a) __builtin_unpack_vector_int128 ((vector __int128_t)(a), 1)
+#endif
+
+/* When we have a load-store in a single-dispatch group and address overlap
+ * such that foward is not allowed (load-hit-store) the group must be flushed.
+ * A group ending NOP prevents the flush.
+ */
+#define GROUP_ENDING_NOP asm("ori 2,2,0" ::: "memory")
+
+#if defined(__BIG_ENDIAN__) && defined (REFLECT)
+#define BYTESWAP_DATA
+#elif defined(__LITTLE_ENDIAN__) && !defined(REFLECT)
+#define BYTESWAP_DATA
+#endif
+
+#ifdef BYTESWAP_DATA
+#define VEC_PERM(vr, va, vb, vc) vr = vec_perm(va, vb,\
+ (__vector unsigned char) vc)
+#if defined(__LITTLE_ENDIAN__)
+/* Byte reverse permute constant LE. */
+static const __vector unsigned long long vperm_const
+ __attribute__ ((aligned(16))) = { 0x08090A0B0C0D0E0FUL,
+ 0x0001020304050607UL };
+#else
+static const __vector unsigned long long vperm_const
+ __attribute__ ((aligned(16))) = { 0x0F0E0D0C0B0A0908UL,
+ 0X0706050403020100UL };
+#endif
+#else
+#define VEC_PERM(vr, va, vb, vc)
+#endif
+
+static unsigned int __attribute__ ((aligned (32)))
+__crc32_vpmsum(unsigned int crc, const void* p, unsigned long len) {
+
+ const __vector unsigned long long vzero = {0,0};
+ const __vector unsigned long long vones = {0xffffffffffffffffUL,
+ 0xffffffffffffffffUL};
+
+#ifdef REFLECT
+ const __vector unsigned long long vmask_32bit =
+ (__vector unsigned long long)vec_sld((__vector unsigned char)vzero,
+ (__vector unsigned char)vones, 4);
+#endif
+
+ const __vector unsigned long long vmask_64bit =
+ (__vector unsigned long long)vec_sld((__vector unsigned char)vzero,
+ (__vector unsigned char)vones, 8);
+
+ __vector unsigned long long vcrc;
+
+ __vector unsigned long long vconst1, vconst2;
+
+ /* vdata0-vdata7 will contain our data (p). */
+ __vector unsigned long long vdata0, vdata1, vdata2, vdata3, vdata4,
+ vdata5, vdata6, vdata7;
+
+ /* v0-v7 will contain our checksums */
+ __vector unsigned long long v0 = {0,0};
+ __vector unsigned long long v1 = {0,0};
+ __vector unsigned long long v2 = {0,0};
+ __vector unsigned long long v3 = {0,0};
+ __vector unsigned long long v4 = {0,0};
+ __vector unsigned long long v5 = {0,0};
+ __vector unsigned long long v6 = {0,0};
+ __vector unsigned long long v7 = {0,0};
+
+
+ /* Vector auxiliary variables. */
+ __vector unsigned long long va0, va1, va2, va3, va4, va5, va6, va7;
+
+ unsigned int result = 0;
+ unsigned int offset; /* Constant table offset. */
+
+ unsigned long i; /* Counter. */
+ unsigned long chunks;
+
+ unsigned long block_size;
+ int next_block = 0;
+
+ /* Align by 128 bits. The last 128 bit block will be processed at end. */
+ unsigned long length = len & 0xFFFFFFFFFFFFFF80UL;
+
+#ifdef REFLECT
+ vcrc = (__vector unsigned long long)__builtin_pack_vector(0UL, crc);
+#else
+ vcrc = (__vector unsigned long long)__builtin_pack_vector(crc, 0UL);
+
+ /* Shift into top 32 bits */
+ vcrc = (__vector unsigned long long)vec_sld((__vector unsigned char)vcrc,
+ (__vector unsigned char)vzero, 4);
+#endif
+
+ /* Short version. */
+ if (len < 256) {
+ /* Calculate where in the constant table we need to start. */
+ offset = 256 - len;
+
+ vconst1 = vec_ld(offset, vcrc_short_const);
+ vdata0 = vec_ld(0, (__vector unsigned long long*) p);
+ VEC_PERM(vdata0, vdata0, vconst1, vperm_const);
+
+ /* xor initial value*/
+ vdata0 = vec_xor(vdata0, vcrc);
+
+ vdata0 = (__vector unsigned long long) __builtin_crypto_vpmsumw
+ ((__vector unsigned int)vdata0, (__vector unsigned int)vconst1);
+ v0 = vec_xor(v0, vdata0);
+
+ for (i = 16; i < len; i += 16) {
+ vconst1 = vec_ld(offset + i, vcrc_short_const);
+ vdata0 = vec_ld(i, (__vector unsigned long long*) p);
+ VEC_PERM(vdata0, vdata0, vconst1, vperm_const);
+ vdata0 = (__vector unsigned long long) __builtin_crypto_vpmsumw
+ ((__vector unsigned int)vdata0, (__vector unsigned int)vconst1);
+ v0 = vec_xor(v0, vdata0);
+ }
+ } else {
+
+ /* Load initial values. */
+ vdata0 = vec_ld(0, (__vector unsigned long long*) p);
+ vdata1 = vec_ld(16, (__vector unsigned long long*) p);
+
+ VEC_PERM(vdata0, vdata0, vdata0, vperm_const);
+ VEC_PERM(vdata1, vdata1, vdata1, vperm_const);
+
+ vdata2 = vec_ld(32, (__vector unsigned long long*) p);
+ vdata3 = vec_ld(48, (__vector unsigned long long*) p);
+
+ VEC_PERM(vdata2, vdata2, vdata2, vperm_const);
+ VEC_PERM(vdata3, vdata3, vdata3, vperm_const);
+
+ vdata4 = vec_ld(64, (__vector unsigned long long*) p);
+ vdata5 = vec_ld(80, (__vector unsigned long long*) p);
+
+ VEC_PERM(vdata4, vdata4, vdata4, vperm_const);
+ VEC_PERM(vdata5, vdata5, vdata5, vperm_const);
+
+ vdata6 = vec_ld(96, (__vector unsigned long long*) p);
+ vdata7 = vec_ld(112, (__vector unsigned long long*) p);
+
+ VEC_PERM(vdata6, vdata6, vdata6, vperm_const);
+ VEC_PERM(vdata7, vdata7, vdata7, vperm_const);
+
+ /* xor in initial value */
+ vdata0 = vec_xor(vdata0, vcrc);
+
+ p = (char *)p + 128;
+
+ do {
+ /* Checksum in blocks of MAX_SIZE. */
+ block_size = length;
+ if (block_size > MAX_SIZE) {
+ block_size = MAX_SIZE;
+ }
+
+ length = length - block_size;
+
+ /*
+ * Work out the offset into the constants table to start at. Each
+ * constant is 16 bytes, and it is used against 128 bytes of input
+ * data - 128 / 16 = 8
+ */
+ offset = (MAX_SIZE/8) - (block_size/8);
+ /* We reduce our final 128 bytes in a separate step */
+ chunks = (block_size/128)-1;
+
+ vconst1 = vec_ld(offset, vcrc_const);
+
+ va0 = __builtin_crypto_vpmsumd ((__vector unsigned long long)vdata0,
+ (__vector unsigned long long)vconst1);
+ va1 = __builtin_crypto_vpmsumd ((__vector unsigned long long)vdata1,
+ (__vector unsigned long long)vconst1);
+ va2 = __builtin_crypto_vpmsumd ((__vector unsigned long long)vdata2,
+ (__vector unsigned long long)vconst1);
+ va3 = __builtin_crypto_vpmsumd ((__vector unsigned long long)vdata3,
+ (__vector unsigned long long)vconst1);
+ va4 = __builtin_crypto_vpmsumd ((__vector unsigned long long)vdata4,
+ (__vector unsigned long long)vconst1);
+ va5 = __builtin_crypto_vpmsumd ((__vector unsigned long long)vdata5,
+ (__vector unsigned long long)vconst1);
+ va6 = __builtin_crypto_vpmsumd ((__vector unsigned long long)vdata6,
+ (__vector unsigned long long)vconst1);
+ va7 = __builtin_crypto_vpmsumd ((__vector unsigned long long)vdata7,
+ (__vector unsigned long long)vconst1);
+
+ if (chunks > 1) {
+ offset += 16;
+ vconst2 = vec_ld(offset, vcrc_const);
+ GROUP_ENDING_NOP;
+
+ vdata0 = vec_ld(0, (__vector unsigned long long*) p);
+ VEC_PERM(vdata0, vdata0, vdata0, vperm_const);
+
+ vdata1 = vec_ld(16, (__vector unsigned long long*) p);
+ VEC_PERM(vdata1, vdata1, vdata1, vperm_const);
+
+ vdata2 = vec_ld(32, (__vector unsigned long long*) p);
+ VEC_PERM(vdata2, vdata2, vdata2, vperm_const);
+
+ vdata3 = vec_ld(48, (__vector unsigned long long*) p);
+ VEC_PERM(vdata3, vdata3, vdata3, vperm_const);
+
+ vdata4 = vec_ld(64, (__vector unsigned long long*) p);
+ VEC_PERM(vdata4, vdata4, vdata4, vperm_const);
+
+ vdata5 = vec_ld(80, (__vector unsigned long long*) p);
+ VEC_PERM(vdata5, vdata5, vdata5, vperm_const);
+
+ vdata6 = vec_ld(96, (__vector unsigned long long*) p);
+ VEC_PERM(vdata6, vdata6, vdata6, vperm_const);
+
+ vdata7 = vec_ld(112, (__vector unsigned long long*) p);
+ VEC_PERM(vdata7, vdata7, vdata7, vperm_const);
+
+ p = (char *)p + 128;
+
+ /*
+ * main loop. We modulo schedule it such that it takes three
+ * iterations to complete - first iteration load, second
+ * iteration vpmsum, third iteration xor.
+ */
+ for (i = 0; i < chunks-2; i++) {
+ vconst1 = vec_ld(offset, vcrc_const);
+ offset += 16;
+ GROUP_ENDING_NOP;
+
+ v0 = vec_xor(v0, va0);
+ va0 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata0, (__vector unsigned long long)vconst2);
+ vdata0 = vec_ld(0, (__vector unsigned long long*) p);
+ VEC_PERM(vdata0, vdata0, vdata0, vperm_const);
+ GROUP_ENDING_NOP;
+
+ v1 = vec_xor(v1, va1);
+ va1 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata1, (__vector unsigned long long)vconst2);
+ vdata1 = vec_ld(16, (__vector unsigned long long*) p);
+ VEC_PERM(vdata1, vdata1, vdata1, vperm_const);
+ GROUP_ENDING_NOP;
+
+ v2 = vec_xor(v2, va2);
+ va2 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata2, (__vector unsigned long long)vconst2);
+ vdata2 = vec_ld(32, (__vector unsigned long long*) p);
+ VEC_PERM(vdata2, vdata2, vdata2, vperm_const);
+ GROUP_ENDING_NOP;
+
+ v3 = vec_xor(v3, va3);
+ va3 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata3, (__vector unsigned long long)vconst2);
+ vdata3 = vec_ld(48, (__vector unsigned long long*) p);
+ VEC_PERM(vdata3, vdata3, vdata3, vperm_const);
+
+ vconst2 = vec_ld(offset, vcrc_const);
+ GROUP_ENDING_NOP;
+
+ v4 = vec_xor(v4, va4);
+ va4 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata4, (__vector unsigned long long)vconst1);
+ vdata4 = vec_ld(64, (__vector unsigned long long*) p);
+ VEC_PERM(vdata4, vdata4, vdata4, vperm_const);
+ GROUP_ENDING_NOP;
+
+ v5 = vec_xor(v5, va5);
+ va5 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata5, (__vector unsigned long long)vconst1);
+ vdata5 = vec_ld(80, (__vector unsigned long long*) p);
+ VEC_PERM(vdata5, vdata5, vdata5, vperm_const);
+ GROUP_ENDING_NOP;
+
+ v6 = vec_xor(v6, va6);
+ va6 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata6, (__vector unsigned long long)vconst1);
+ vdata6 = vec_ld(96, (__vector unsigned long long*) p);
+ VEC_PERM(vdata6, vdata6, vdata6, vperm_const);
+ GROUP_ENDING_NOP;
+
+ v7 = vec_xor(v7, va7);
+ va7 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata7, (__vector unsigned long long)vconst1);
+ vdata7 = vec_ld(112, (__vector unsigned long long*) p);
+ VEC_PERM(vdata7, vdata7, vdata7, vperm_const);
+
+ p = (char *)p + 128;
+ }
+
+ /* First cool down*/
+ vconst1 = vec_ld(offset, vcrc_const);
+ offset += 16;
+
+ v0 = vec_xor(v0, va0);
+ va0 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata0, (__vector unsigned long long)vconst1);
+ GROUP_ENDING_NOP;
+
+ v1 = vec_xor(v1, va1);
+ va1 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata1, (__vector unsigned long long)vconst1);
+ GROUP_ENDING_NOP;
+
+ v2 = vec_xor(v2, va2);
+ va2 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata2, (__vector unsigned long long)vconst1);
+ GROUP_ENDING_NOP;
+
+ v3 = vec_xor(v3, va3);
+ va3 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata3, (__vector unsigned long long)vconst1);
+ GROUP_ENDING_NOP;
+
+ v4 = vec_xor(v4, va4);
+ va4 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata4, (__vector unsigned long long)vconst1);
+ GROUP_ENDING_NOP;
+
+ v5 = vec_xor(v5, va5);
+ va5 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata5, (__vector unsigned long long)vconst1);
+ GROUP_ENDING_NOP;
+
+ v6 = vec_xor(v6, va6);
+ va6 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata6, (__vector unsigned long long)vconst1);
+ GROUP_ENDING_NOP;
+
+ v7 = vec_xor(v7, va7);
+ va7 = __builtin_crypto_vpmsumd ((__vector unsigned long
+ long)vdata7, (__vector unsigned long long)vconst1);
+ }/* else */
+
+ /* Second cool down. */
+ v0 = vec_xor(v0, va0);
+ v1 = vec_xor(v1, va1);
+ v2 = vec_xor(v2, va2);
+ v3 = vec_xor(v3, va3);
+ v4 = vec_xor(v4, va4);
+ v5 = vec_xor(v5, va5);
+ v6 = vec_xor(v6, va6);
+ v7 = vec_xor(v7, va7);
+
+#ifdef REFLECT
+ /*
+ * vpmsumd produces a 96 bit result in the least significant bits
+ * of the register. Since we are bit reflected we have to shift it
+ * left 32 bits so it occupies the least significant bits in the
+ * bit reflected domain.
+ */
+ v0 = (__vector unsigned long long)vec_sld((__vector unsigned char)v0,
+ (__vector unsigned char)vzero, 4);
+ v1 = (__vector unsigned long long)vec_sld((__vector unsigned char)v1,
+ (__vector unsigned char)vzero, 4);
+ v2 = (__vector unsigned long long)vec_sld((__vector unsigned char)v2,
+ (__vector unsigned char)vzero, 4);
+ v3 = (__vector unsigned long long)vec_sld((__vector unsigned char)v3,
+ (__vector unsigned char)vzero, 4);
+ v4 = (__vector unsigned long long)vec_sld((__vector unsigned char)v4,
+ (__vector unsigned char)vzero, 4);
+ v5 = (__vector unsigned long long)vec_sld((__vector unsigned char)v5,
+ (__vector unsigned char)vzero, 4);
+ v6 = (__vector unsigned long long)vec_sld((__vector unsigned char)v6,
+ (__vector unsigned char)vzero, 4);
+ v7 = (__vector unsigned long long)vec_sld((__vector unsigned char)v7,
+ (__vector unsigned char)vzero, 4);
+#endif
+
+ /* xor with the last 1024 bits. */
+ va0 = vec_ld(0, (__vector unsigned long long*) p);
+ VEC_PERM(va0, va0, va0, vperm_const);
+
+ va1 = vec_ld(16, (__vector unsigned long long*) p);
+ VEC_PERM(va1, va1, va1, vperm_const);
+
+ va2 = vec_ld(32, (__vector unsigned long long*) p);
+ VEC_PERM(va2, va2, va2, vperm_const);
+
+ va3 = vec_ld(48, (__vector unsigned long long*) p);
+ VEC_PERM(va3, va3, va3, vperm_const);
+
+ va4 = vec_ld(64, (__vector unsigned long long*) p);
+ VEC_PERM(va4, va4, va4, vperm_const);
+
+ va5 = vec_ld(80, (__vector unsigned long long*) p);
+ VEC_PERM(va5, va5, va5, vperm_const);
+
+ va6 = vec_ld(96, (__vector unsigned long long*) p);
+ VEC_PERM(va6, va6, va6, vperm_const);
+
+ va7 = vec_ld(112, (__vector unsigned long long*) p);
+ VEC_PERM(va7, va7, va7, vperm_const);
+
+ p = (char *)p + 128;
+
+ vdata0 = vec_xor(v0, va0);
+ vdata1 = vec_xor(v1, va1);
+ vdata2 = vec_xor(v2, va2);
+ vdata3 = vec_xor(v3, va3);
+ vdata4 = vec_xor(v4, va4);
+ vdata5 = vec_xor(v5, va5);
+ vdata6 = vec_xor(v6, va6);
+ vdata7 = vec_xor(v7, va7);
+
+ /* Check if we have more blocks to process */
+ next_block = 0;
+ if (length != 0) {
+ next_block = 1;
+
+ /* zero v0-v7 */
+ v0 = vec_xor(v0, v0);
+ v1 = vec_xor(v1, v1);
+ v2 = vec_xor(v2, v2);
+ v3 = vec_xor(v3, v3);
+ v4 = vec_xor(v4, v4);
+ v5 = vec_xor(v5, v5);
+ v6 = vec_xor(v6, v6);
+ v7 = vec_xor(v7, v7);
+ }
+ length = length + 128;
+
+ } while (next_block);
+
+ /* Calculate how many bytes we have left. */
+ length = (len & 127);
+
+ /* Calculate where in (short) constant table we need to start. */
+ offset = 128 - length;
+
+ v0 = vec_ld(offset, vcrc_short_const);
+ v1 = vec_ld(offset + 16, vcrc_short_const);
+ v2 = vec_ld(offset + 32, vcrc_short_const);
+ v3 = vec_ld(offset + 48, vcrc_short_const);
+ v4 = vec_ld(offset + 64, vcrc_short_const);
+ v5 = vec_ld(offset + 80, vcrc_short_const);
+ v6 = vec_ld(offset + 96, vcrc_short_const);
+ v7 = vec_ld(offset + 112, vcrc_short_const);
+
+ offset += 128;
+
+ v0 = (__vector unsigned long long)__builtin_crypto_vpmsumw (
+ (__vector unsigned int)vdata0,(__vector unsigned int)v0);
+ v1 = (__vector unsigned long long)__builtin_crypto_vpmsumw (
+ (__vector unsigned int)vdata1,(__vector unsigned int)v1);
+ v2 = (__vector unsigned long long)__builtin_crypto_vpmsumw (
+ (__vector unsigned int)vdata2,(__vector unsigned int)v2);
+ v3 = (__vector unsigned long long)__builtin_crypto_vpmsumw (
+ (__vector unsigned int)vdata3,(__vector unsigned int)v3);
+ v4 = (__vector unsigned long long)__builtin_crypto_vpmsumw (
+ (__vector unsigned int)vdata4,(__vector unsigned int)v4);
+ v5 = (__vector unsigned long long)__builtin_crypto_vpmsumw (
+ (__vector unsigned int)vdata5,(__vector unsigned int)v5);
+ v6 = (__vector unsigned long long)__builtin_crypto_vpmsumw (
+ (__vector unsigned int)vdata6,(__vector unsigned int)v6);
+ v7 = (__vector unsigned long long)__builtin_crypto_vpmsumw (
+ (__vector unsigned int)vdata7,(__vector unsigned int)v7);
+
+ /* Now reduce the tail (0-112 bytes). */
+ for (i = 0; i < length; i+=16) {
+ vdata0 = vec_ld(i,(__vector unsigned long long*)p);
+ VEC_PERM(vdata0, vdata0, vdata0, vperm_const);
+ va0 = vec_ld(offset + i,vcrc_short_const);
+ va0 = (__vector unsigned long long)__builtin_crypto_vpmsumw (
+ (__vector unsigned int)vdata0,(__vector unsigned int)va0);
+ v0 = vec_xor(v0, va0);
+ }
+
+ /* xor all parallel chunks together. */
+ v0 = vec_xor(v0, v1);
+ v2 = vec_xor(v2, v3);
+ v4 = vec_xor(v4, v5);
+ v6 = vec_xor(v6, v7);
+
+ v0 = vec_xor(v0, v2);
+ v4 = vec_xor(v4, v6);
+
+ v0 = vec_xor(v0, v4);
+ }
+
+ /* Barrett Reduction */
+ vconst1 = vec_ld(0, v_Barrett_const);
+ vconst2 = vec_ld(16, v_Barrett_const);
+
+ v1 = (__vector unsigned long long)vec_sld((__vector unsigned char)v0,
+ (__vector unsigned char)v0, 8);
+ v0 = vec_xor(v1,v0);
+
+#ifdef REFLECT
+ /* shift left one bit */
+ __vector unsigned char vsht_splat = vec_splat_u8 (1);
+ v0 = (__vector unsigned long long)vec_sll ((__vector unsigned char)v0,
+ vsht_splat);
+#endif
+
+ v0 = vec_and(v0, vmask_64bit);
+
+#ifndef REFLECT
+
+ /*
+ * Now for the actual algorithm. The idea is to calculate q,
+ * the multiple of our polynomial that we need to subtract. By
+ * doing the computation 2x bits higher (ie 64 bits) and shifting the
+ * result back down 2x bits, we round down to the nearest multiple.
+ */
+
+ /* ma */
+ v1 = __builtin_crypto_vpmsumd ((__vector unsigned long long)v0,
+ (__vector unsigned long long)vconst1);
+ /* q = floor(ma/(2^64)) */
+ v1 = (__vector unsigned long long)vec_sld ((__vector unsigned char)vzero,
+ (__vector unsigned char)v1, 8);
+ /* qn */
+ v1 = __builtin_crypto_vpmsumd ((__vector unsigned long long)v1,
+ (__vector unsigned long long)vconst2);
+ /* a - qn, subtraction is xor in GF(2) */
+ v0 = vec_xor (v0, v1);
+ /*
+ * Get the result into r3. We need to shift it left 8 bytes:
+ * V0 [ 0 1 2 X ]
+ * V0 [ 0 X 2 3 ]
+ */
+ result = __builtin_unpack_vector_1 (v0);
+#else
+
+ /*
+ * The reflected version of Barrett reduction. Instead of bit
+ * reflecting our data (which is expensive to do), we bit reflect our
+ * constants and our algorithm, which means the intermediate data in
+ * our vector registers goes from 0-63 instead of 63-0. We can reflect
+ * the algorithm because we don't carry in mod 2 arithmetic.
+ */
+
+ /* bottom 32 bits of a */
+ v1 = vec_and(v0, vmask_32bit);
+
+ /* ma */
+ v1 = __builtin_crypto_vpmsumd ((__vector unsigned long long)v1,
+ (__vector unsigned long long)vconst1);
+
+ /* bottom 32bits of ma */
+ v1 = vec_and(v1, vmask_32bit);
+ /* qn */
+ v1 = __builtin_crypto_vpmsumd ((__vector unsigned long long)v1,
+ (__vector unsigned long long)vconst2);
+ /* a - qn, subtraction is xor in GF(2) */
+ v0 = vec_xor (v0, v1);
+
+ /*
+ * Since we are bit reflected, the result (ie the low 32 bits) is in
+ * the high 32 bits. We just need to shift it left 4 bytes
+ * V0 [ 0 1 X 3 ]
+ * V0 [ 0 X 2 3 ]
+ */
+
+ /* shift result into top 64 bits of */
+ v0 = (__vector unsigned long long)vec_sld((__vector unsigned char)v0,
+ (__vector unsigned char)vzero, 4);
+
+ result = __builtin_unpack_vector_0 (v0);
+#endif
+
+ return result;
+}
diff --git a/contrib/power/crc32_z_resolver.c b/contrib/power/crc32_z_resolver.c
new file mode 100644
index 0000000..f4e9aa4
--- /dev/null
+++ b/contrib/power/crc32_z_resolver.c
@@ -0,0 +1,15 @@
+/* Copyright (C) 2019 Matheus Castanho <msc@linux.ibm.com>, IBM
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+#include "../gcc/zifunc.h"
+#include "power.h"
+
+Z_IFUNC(crc32_z) {
+#ifdef Z_POWER8
+ if (__builtin_cpu_supports("arch_2_07"))
+ return _crc32_z_power8;
+#endif
+
+ return crc32_z_default;
+}
diff --git a/contrib/power/power.h b/contrib/power/power.h
index b42c7d6..79123aa 100644
--- a/contrib/power/power.h
+++ b/contrib/power/power.h
@@ -2,3 +2,7 @@
* 2019 Rogerio Alves <rogerio.alves@ibm.com>, IBM
* For conditions of distribution and use, see copyright notice in zlib.h
*/
+
+#include "../../zconf.h"
+
+unsigned long _crc32_z_power8(unsigned long, const Bytef *, z_size_t);
diff --git a/crc32.c b/crc32.c
index f8357b0..4e5830b 100644
--- a/crc32.c
+++ b/crc32.c
@@ -745,6 +745,13 @@ local z_word_t crc_word_big(data)
#endif
/* ========================================================================= */
+#ifdef Z_POWER_OPT
+/* Rename function so resolver can use its symbol. The default version will be
+ * returned by the resolver if the host has no support for an optimized version.
+ */
+#define crc32_z crc32_z_default
+#endif /* Z_POWER_OPT */
+
unsigned long ZEXPORT crc32_z(crc, buf, len)
unsigned long crc;
const unsigned char FAR *buf;
@@ -1066,6 +1073,11 @@ unsigned long ZEXPORT crc32_z(crc, buf, len)
return crc ^ 0xffffffff;
}
+#ifdef Z_POWER_OPT
+#undef crc32_z
+#include "contrib/power/crc32_z_resolver.c"
+#endif /* Z_POWER_OPT */
+
#endif
/* ========================================================================= */
diff --git a/test/crc32_test.c b/test/crc32_test.c
new file mode 100644
index 0000000..3155553
--- /dev/null
+++ b/test/crc32_test.c
@@ -0,0 +1,205 @@
+/* crc32_tes.c -- unit test for crc32 in the zlib compression library
+ * Copyright (C) 1995-2006, 2010, 2011, 2016, 2019 Rogerio Alves
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+#include "zlib.h"
+#include <stdio.h>
+
+#ifdef STDC
+# include <string.h>
+# include <stdlib.h>
+#endif
+
+void test_crc32 OF((uLong crc, Byte* buf, z_size_t len, uLong chk, int line));
+int main OF((void));
+
+typedef struct {
+ int line;
+ uLong crc;
+ char* buf;
+ int len;
+ uLong expect;
+} crc32_test;
+
+void test_crc32(crc, buf, len, chk, line)
+ uLong crc;
+ Byte *buf;
+ z_size_t len;
+ uLong chk;
+ int line;
+{
+ uLong res = crc32(crc, buf, len);
+ if (res != chk) {
+ fprintf(stderr, "FAIL [%d]: crc32 returned 0x%08X expected 0x%08X\n",
+ line, (unsigned int)res, (unsigned int)chk);
+ exit(1);
+ }
+}
+
+static const crc32_test tests[] = {
+ {__LINE__, 0x0, 0x0, 0, 0x0},
+ {__LINE__, 0xffffffff, 0x0, 0, 0x0},
+ {__LINE__, 0x0, 0x0, 255, 0x0}, /* BZ 174799. */
+ {__LINE__, 0x0, 0x0, 256, 0x0},
+ {__LINE__, 0x0, 0x0, 257, 0x0},
+ {__LINE__, 0x0, 0x0, 32767, 0x0},
+ {__LINE__, 0x0, 0x0, 32768, 0x0},
+ {__LINE__, 0x0, 0x0, 32769, 0x0},
+ {__LINE__, 0x0, "", 0, 0x0},
+ {__LINE__, 0xffffffff, "", 0, 0xffffffff},
+ {__LINE__, 0x0, "abacus", 6, 0xc3d7115b},
+ {__LINE__, 0x0, "backlog", 7, 0x269205},
+ {__LINE__, 0x0, "campfire", 8, 0x22a515f8},
+ {__LINE__, 0x0, "delta", 5, 0x9643fed9},
+ {__LINE__, 0x0, "executable", 10, 0xd68eda01},
+ {__LINE__, 0x0, "file", 4, 0x8c9f3610},
+ {__LINE__, 0x0, "greatest", 8, 0xc1abd6cd},
+ {__LINE__, 0x0, "hello", 5, 0x3610a686},
+ {__LINE__, 0x0, "inverter", 8, 0xc9e962c9},
+ {__LINE__, 0x0, "jigsaw", 6, 0xce4e3f69},
+ {__LINE__, 0x0, "karate", 6, 0x890be0e2},
+ {__LINE__, 0x0, "landscape", 9, 0xc4e0330b},
+ {__LINE__, 0x0, "machine", 7, 0x1505df84},
+ {__LINE__, 0x0, "nanometer", 9, 0xd4e19f39},
+ {__LINE__, 0x0, "oblivion", 8, 0xdae9de77},
+ {__LINE__, 0x0, "panama", 6, 0x66b8979c},
+ {__LINE__, 0x0, "quest", 5, 0x4317f817},
+ {__LINE__, 0x0, "resource", 8, 0xbc91f416},
+ {__LINE__, 0x0, "secret", 6, 0x5ca2e8e5},
+ {__LINE__, 0x0, "test", 4, 0xd87f7e0c},
+ {__LINE__, 0x0, "ultimate", 8, 0x3fc79b0b},
+ {__LINE__, 0x0, "vector", 6, 0x1b6e485b},
+ {__LINE__, 0x0, "walrus", 6, 0xbe769b97},
+ {__LINE__, 0x0, "xeno", 4, 0xe7a06444},
+ {__LINE__, 0x0, "yelling", 7, 0xfe3944e5},
+ {__LINE__, 0x0, "zlib", 4, 0x73887d3a},
+ {__LINE__, 0x0, "4BJD7PocN1VqX0jXVpWB", 20, 0xd487a5a1},
+ {__LINE__, 0x0, "F1rPWI7XvDs6nAIRx41l", 20, 0x61a0132e},
+ {__LINE__, 0x0, "ldhKlsVkPFOveXgkGtC2", 20, 0xdf02f76},
+ {__LINE__, 0x0, "5KKnGOOrs8BvJ35iKTOS", 20, 0x579b2b0a},
+ {__LINE__, 0x0, "0l1tw7GOcem06Ddu7yn4", 20, 0xf7d16e2d},
+ {__LINE__, 0x0, "MCr47CjPIn9R1IvE1Tm5", 20, 0x731788f5},
+ {__LINE__, 0x0, "UcixbzPKTIv0SvILHVdO", 20, 0x7112bb11},
+ {__LINE__, 0x0, "dGnAyAhRQDsWw0ESou24", 20, 0xf32a0dac},
+ {__LINE__, 0x0, "di0nvmY9UYMYDh0r45XT", 20, 0x625437bb},
+ {__LINE__, 0x0, "2XKDwHfAhFsV0RhbqtvH", 20, 0x896930f9},
+ {__LINE__, 0x0, "ZhrANFIiIvRnqClIVyeD", 20, 0x8579a37},
+ {__LINE__, 0x0, "v7Q9ehzioTOVeDIZioT1", 20, 0x632aa8e0},
+ {__LINE__, 0x0, "Yod5hEeKcYqyhfXbhxj2", 20, 0xc829af29},
+ {__LINE__, 0x0, "GehSWY2ay4uUKhehXYb0", 20, 0x1b08b7e8},
+ {__LINE__, 0x0, "kwytJmq6UqpflV8Y8GoE", 20, 0x4e33b192},
+ {__LINE__, 0x0, "70684206568419061514", 20, 0x59a179f0},
+ {__LINE__, 0x0, "42015093765128581010", 20, 0xcd1013d7},
+ {__LINE__, 0x0, "88214814356148806939", 20, 0xab927546},
+ {__LINE__, 0x0, "43472694284527343838", 20, 0x11f3b20c},
+ {__LINE__, 0x0, "49769333513942933689", 20, 0xd562d4ca},
+ {__LINE__, 0x0, "54979784887993251199", 20, 0x233395f7},
+ {__LINE__, 0x0, "58360544869206793220", 20, 0x2d167fd5},
+ {__LINE__, 0x0, "27347953487840714234", 20, 0x8b5108ba},
+ {__LINE__, 0x0, "07650690295365319082", 20, 0xc46b3cd8},
+ {__LINE__, 0x0, "42655507906821911703", 20, 0xc10b2662},
+ {__LINE__, 0x0, "29977409200786225655", 20, 0xc9a0f9d2},
+ {__LINE__, 0x0, "85181542907229116674", 20, 0x9341357b},
+ {__LINE__, 0x0, "87963594337989416799", 20, 0xf0424937},
+ {__LINE__, 0x0, "21395988329504168551", 20, 0xd7c4c31f},
+ {__LINE__, 0x0, "51991013580943379423", 20, 0xf11edcc4},
+ {__LINE__, 0x0, "*]+@!);({_$;}[_},?{?;(_?,=-][@", 30, 0x40795df4},
+ {__LINE__, 0x0, "_@:_).&(#.[:[{[:)$++-($_;@[)}+", 30, 0xdd61a631},
+ {__LINE__, 0x0, "&[!,[$_==}+.]@!;*(+},[;:)$;)-@", 30, 0xca907a99},
+ {__LINE__, 0x0, "]{.[.+?+[[=;[?}_#&;[=)__$$:+=_", 30, 0xf652deac},
+ {__LINE__, 0x0, "-%.)=/[@].:.(:,()$;=%@-$?]{%+%", 30, 0xaf39a5a9},
+ {__LINE__, 0x0, "+]#$(@&.=:,*];/.!]%/{:){:@(;)$", 30, 0x6bebb4cf},
+ {__LINE__, 0x0, ")-._.:?[&:.=+}(*$/=!.${;(=$@!}", 30, 0x76430bac},
+ {__LINE__, 0x0, ":(_*&%/[[}+,?#$&*+#[([*-/#;%(]", 30, 0x6c80c388},
+ {__LINE__, 0x0, "{[#-;:$/{)(+[}#]/{&!%(@)%:@-$:", 30, 0xd54d977d},
+ {__LINE__, 0x0, "_{$*,}(&,@.)):=!/%(&(,,-?$}}}!", 30, 0xe3966ad5},
+ {__LINE__, 0x0, "e$98KNzqaV)Y:2X?]77].{gKRD4G5{mHZk,Z)SpU%L3FSgv!Wb8MLAFdi{+fp)c,@8m6v)yXg@]HBDFk?.4&}g5_udE*JHCiH=aL", 100, 0xe7c71db9},
+ {__LINE__, 0x0, "r*Fd}ef+5RJQ;+W=4jTR9)R*p!B;]Ed7tkrLi;88U7g@3v!5pk2X6D)vt,.@N8c]@yyEcKi[vwUu@.Ppm@C6%Mv*3Nw}Y,58_aH)", 100, 0xeaa52777},
+ {__LINE__, 0x0, "h{bcmdC+a;t+Cf{6Y_dFq-{X4Yu&7uNfVDh?q&_u.UWJU],-GiH7ADzb7-V.Q%4=+v!$L9W+T=bP]$_:]Vyg}A.ygD.r;h-D]m%&", 100, 0xcd472048},
+ {__LINE__, 0x7a30360d, "abacus", 6, 0xf8655a84},
+ {__LINE__, 0x6fd767ee, "backlog", 7, 0x1ed834b1},
+ {__LINE__, 0xefeb7589, "campfire", 8, 0x686cfca},
+ {__LINE__, 0x61cf7e6b, "delta", 5, 0x1554e4b1},
+ {__LINE__, 0xdc712e2, "executable", 10, 0x761b4254},
+ {__LINE__, 0xad23c7fd, "file", 4, 0x7abdd09b},
+ {__LINE__, 0x85cb2317, "greatest", 8, 0x4ba91c6b},
+ {__LINE__, 0x9eed31b0, "inverter", 8, 0xd5e78ba5},
+ {__LINE__, 0xb94f34ca, "jigsaw", 6, 0x23649109},
+ {__LINE__, 0xab058a2, "karate", 6, 0xc5591f41},
+ {__LINE__, 0x5bff2b7a, "landscape", 9, 0xf10eb644},
+ {__LINE__, 0x605c9a5f, "machine", 7, 0xbaa0a636},
+ {__LINE__, 0x51bdeea5, "nanometer", 9, 0x6af89afb},
+ {__LINE__, 0x85c21c79, "oblivion", 8, 0xecae222b},
+ {__LINE__, 0x97216f56, "panama", 6, 0x47dffac4},
+ {__LINE__, 0x18444af2, "quest", 5, 0x70c2fe36},
+ {__LINE__, 0xbe6ce359, "resource", 8, 0x1471d925},
+ {__LINE__, 0x843071f1, "secret", 6, 0x50c9a0db},
+ {__LINE__, 0xf2480c60, "ultimate", 8, 0xf973daf8},
+ {__LINE__, 0x2d2feb3d, "vector", 6, 0x344ac03d},
+ {__LINE__, 0x7490310a, "walrus", 6, 0x6d1408ef},
+ {__LINE__, 0x97d247d4, "xeno", 4, 0xe62670b5},
+ {__LINE__, 0x93cf7599, "yelling", 7, 0x1b36da38},
+ {__LINE__, 0x73c84278, "zlib", 4, 0x6432d127},
+ {__LINE__, 0x228a87d1, "4BJD7PocN1VqX0jXVpWB", 20, 0x997107d0},
+ {__LINE__, 0xa7a048d0, "F1rPWI7XvDs6nAIRx41l", 20, 0xdc567274},
+ {__LINE__, 0x1f0ded40, "ldhKlsVkPFOveXgkGtC2", 20, 0xdcc63870},
+ {__LINE__, 0xa804a62f, "5KKnGOOrs8BvJ35iKTOS", 20, 0x6926cffd},
+ {__LINE__, 0x508fae6a, "0l1tw7GOcem06Ddu7yn4", 20, 0xb52b38bc},
+ {__LINE__, 0xe5adaf4f, "MCr47CjPIn9R1IvE1Tm5", 20, 0xf83b8178},
+ {__LINE__, 0x67136a40, "UcixbzPKTIv0SvILHVdO", 20, 0xc5213070},
+ {__LINE__, 0xb00c4a10, "dGnAyAhRQDsWw0ESou24", 20, 0xbc7648b0},
+ {__LINE__, 0x2e0c84b5, "di0nvmY9UYMYDh0r45XT", 20, 0xd8123a72},
+ {__LINE__, 0x81238d44, "2XKDwHfAhFsV0RhbqtvH", 20, 0xd5ac5620},
+ {__LINE__, 0xf853aa92, "ZhrANFIiIvRnqClIVyeD", 20, 0xceae099d},
+ {__LINE__, 0x5a692325, "v7Q9ehzioTOVeDIZioT1", 20, 0xb07d2b24},
+ {__LINE__, 0x3275b9f, "Yod5hEeKcYqyhfXbhxj2", 20, 0x24ce91df},
+ {__LINE__, 0x38371feb, "GehSWY2ay4uUKhehXYb0", 20, 0x707b3b30},
+ {__LINE__, 0xafc8bf62, "kwytJmq6UqpflV8Y8GoE", 20, 0x16abc6a9},
+ {__LINE__, 0x9b07db73, "70684206568419061514", 20, 0xae1fb7b7},
+ {__LINE__, 0xe75b214, "42015093765128581010", 20, 0xd4eecd2d},
+ {__LINE__, 0x72d0fe6f, "88214814356148806939", 20, 0x4660ec7},
+ {__LINE__, 0xf857a4b1, "43472694284527343838", 20, 0xfd8afdf7},
+ {__LINE__, 0x54b8e14, "49769333513942933689", 20, 0xc6d1b5f2},
+ {__LINE__, 0xd6aa5616, "54979784887993251199", 20, 0x32476461},
+ {__LINE__, 0x11e63098, "58360544869206793220", 20, 0xd917cf1a},
+ {__LINE__, 0xbe92385, "27347953487840714234", 20, 0x4ad14a12},
+ {__LINE__, 0x49511de0, "07650690295365319082", 20, 0xe37b5c6c},
+ {__LINE__, 0x3db13bc1, "42655507906821911703", 20, 0x7cc497f1},
+ {__LINE__, 0xbb899bea, "29977409200786225655", 20, 0x99781bb2},
+ {__LINE__, 0xf6cd9436, "85181542907229116674", 20, 0x132256a1},
+ {__LINE__, 0x9109e6c3, "87963594337989416799", 20, 0xbfdb2c83},
+ {__LINE__, 0x75770fc, "21395988329504168551", 20, 0x8d9d1e81},
+ {__LINE__, 0x69b1d19b, "51991013580943379423", 20, 0x7b6d4404},
+ {__LINE__, 0xc6132975, "*]+@!);({_$;}[_},?{?;(_?,=-][@", 30, 0x8619f010},
+ {__LINE__, 0xd58cb00c, "_@:_).&(#.[:[{[:)$++-($_;@[)}+", 30, 0x15746ac3},
+ {__LINE__, 0xb63b8caa, "&[!,[$_==}+.]@!;*(+},[;:)$;)-@", 30, 0xaccf812f},
+ {__LINE__, 0x8a45a2b8, "]{.[.+?+[[=;[?}_#&;[=)__$$:+=_", 30, 0x78af45de},
+ {__LINE__, 0xcbe95b78, "-%.)=/[@].:.(:,()$;=%@-$?]{%+%", 30, 0x25b06b59},
+ {__LINE__, 0x4ef8a54b, "+]#$(@&.=:,*];/.!]%/{:){:@(;)$", 30, 0x4ba0d08f},
+ {__LINE__, 0x76ad267a, ")-._.:?[&:.=+}(*$/=!.${;(=$@!}", 30, 0xe26b6aac},
+ {__LINE__, 0x569e613c, ":(_*&%/[[}+,?#$&*+#[([*-/#;%(]", 30, 0x7e2b0a66},
+ {__LINE__, 0x36aa61da, "{[#-;:$/{)(+[}#]/{&!%(@)%:@-$:", 30, 0xb3430dc7},
+ {__LINE__, 0xf67222df, "_{$*,}(&,@.)):=!/%(&(,,-?$}}}!", 30, 0x626c17a},
+ {__LINE__, 0x74b34fd3, "e$98KNzqaV)Y:2X?]77].{gKRD4G5{mHZk,Z)SpU%L3FSgv!Wb8MLAFdi{+fp)c,@8m6v)yXg@]HBDFk?.4&}g5_udE*JHCiH=aL", 100, 0xccf98060},
+ {__LINE__, 0x351fd770, "r*Fd}ef+5RJQ;+W=4jTR9)R*p!B;]Ed7tkrLi;88U7g@3v!5pk2X6D)vt,.@N8c]@yyEcKi[vwUu@.Ppm@C6%Mv*3Nw}Y,58_aH)", 100, 0xd8b95312},
+ {__LINE__, 0xc45aef77, "h{bcmdC+a;t+Cf{6Y_dFq-{X4Yu&7uNfVDh?q&_u.UWJU],-GiH7ADzb7-V.Q%4=+v!$L9W+T=bP]$_:]Vyg}A.ygD.r;h-D]m%&", 100, 0xbb1c9912},
+ {__LINE__, 0xc45aef77, "h{bcmdC+a;t+Cf{6Y_dFq-{X4Yu&7uNfVDh?q&_u.UWJU],-GiH7ADzb7-V.Q%4=+v!$L9W+T=bP]$_:]Vyg}A.ygD.r;h-D]m%&"
+ "h{bcmdC+a;t+Cf{6Y_dFq-{X4Yu&7uNfVDh?q&_u.UWJU],-GiH7ADzb7-V.Q%4=+v!$L9W+T=bP]$_:]Vyg}A.ygD.r;h-D]m%&"
+ "h{bcmdC+a;t+Cf{6Y_dFq-{X4Yu&7uNfVDh?q&_u.UWJU],-GiH7ADzb7-V.Q%4=+v!$L9W+T=bP]$_:]Vyg}A.ygD.r;h-D]m%&"
+ "h{bcmdC+a;t+Cf{6Y_dFq-{X4Yu&7uNfVDh?q&_u.UWJU],-GiH7ADzb7-V.Q%4=+v!$L9W+T=bP]$_:]Vyg}A.ygD.r;h-D]m%&"
+ "h{bcmdC+a;t+Cf{6Y_dFq-{X4Yu&7uNfVDh?q&_u.UWJU],-GiH7ADzb7-V.Q%4=+v!$L9W+T=bP]$_:]Vyg}A.ygD.r;h-D]m%&"
+ "h{bcmdC+a;t+Cf{6Y_dFq-{X4Yu&7uNfVDh?q&_u.UWJU],-GiH7ADzb7-V.Q%4=+v!$L9W+T=bP]$_:]Vyg}A.ygD.r;h-D]m%&", 600, 0x888AFA5B}
+};
+
+static const int test_size = sizeof(tests) / sizeof(tests[0]);
+
+int main(void)
+{
+ int i;
+ for (i = 0; i < test_size; i++) {
+ test_crc32(tests[i].crc, (Byte*) tests[i].buf, tests[i].len,
+ tests[i].expect, tests[i].line);
+ }
+ return 0;
+}
--
2.37.3
From e8c61767464de8d063366117f508359e5ca40a50 Mon Sep 17 00:00:00 2001
From: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
Date: Wed, 25 Mar 2020 12:16:41 -0300
Subject: [PATCH 3/3] Fix clang's behavior on versions >= 7
Clang 7 changed the behavior of vec_xxpermdi in order to match GCC's
behavior. After this change, code that used to work on Clang 6 stopped
to work on Clang >= 7.
Tested on Clang 6, 7, 8 and 9.
Reference: https://bugs.llvm.org/show_bug.cgi?id=38192
Signed-off-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
---
contrib/power/clang_workaround.h | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/contrib/power/clang_workaround.h b/contrib/power/clang_workaround.h
index b5e7dae..915f7e5 100644
--- a/contrib/power/clang_workaround.h
+++ b/contrib/power/clang_workaround.h
@@ -39,7 +39,12 @@ __vector unsigned long long __builtin_pack_vector (unsigned long __a,
return __v;
}
-#ifndef vec_xxpermdi
+/*
+ * Clang 7 changed the behavior of vec_xxpermdi in order to provide the same
+ * behavior of GCC. That means code adapted to Clang >= 7 does not work on
+ * Clang <= 6. So, fallback to __builtin_unpack_vector() on Clang <= 6.
+ */
+#if !defined vec_xxpermdi || __clang_major__ <= 6
static inline
unsigned long __builtin_unpack_vector (__vector unsigned long long __v,
@@ -62,9 +67,9 @@ static inline
unsigned long __builtin_unpack_vector_0 (__vector unsigned long long __v)
{
#if defined(__BIG_ENDIAN__)
- return vec_xxpermdi(__v, __v, 0x0)[1];
- #else
return vec_xxpermdi(__v, __v, 0x0)[0];
+ #else
+ return vec_xxpermdi(__v, __v, 0x3)[0];
#endif
}
@@ -72,9 +77,9 @@ static inline
unsigned long __builtin_unpack_vector_1 (__vector unsigned long long __v)
{
#if defined(__BIG_ENDIAN__)
- return vec_xxpermdi(__v, __v, 0x3)[1];
- #else
return vec_xxpermdi(__v, __v, 0x3)[0];
+ #else
+ return vec_xxpermdi(__v, __v, 0x0)[0];
#endif
}
#endif /* vec_xxpermdi */
--
2.37.3