Import 3.3.3

ChangeLog

@@ -1,3 +1,132 @@
+Sat Nov 24 22:37:54 EST 2012  stevenj@fftw.org
+  * fixed deadlock bug caused by bogosity flag getting out of synch between processes; thanks to Michael Pippig for the bug report
+
+    M ./kernel/ifftw.h +1
+    M ./kernel/planner.c -3 +6
+    M ./mpi/api.c +12
+
+Wed Nov 21 18:34:29 EST 2012  athena@fftw.org
+  * Updated NEWS
+
+    M ./NEWS -2 +7
+
+Wed Nov 21 18:33:15 EST 2012  athena@fftw.org
+  * use 2x2 AVX transposition instead of individual stores.
+
+  This seems to improve single-precision AVX on Sandy Bridge machines.
+
+
+    M ./simd-support/simd-avx.h -2 +14
+
+Tue Nov 20 12:18:00 EST 2012  stevenj@fftw.org
+  * revert part of Taylor patch to acx_mpi.m4: do not link -lmpi if mpicc works without libraries, as -lmpi may be some completely different MPI implementation
+
+    M ./m4/acx_mpi.m4 -3 +3
+
+Tue Nov 20 11:44:57 EST 2012  stevenj@fftw.org
+  * fix deadlock bug (thanks to Michael Pippig for the bug report and patch, and to Graham Dennis for the bug report) in which some processes called MPI_Alltoall and some called MPI_Alltoallv
+
+    M ./mpi/transpose-alltoall.c -3 +2
+
+Mon Oct 29 15:20:01 EDT 2012  athena@fftw.org
+  * fix texinfo quirk
+
+    M ./doc/tutorial.texi -2 +2
+
+Mon Oct 29 09:16:43 EDT 2012  athena@fftw.org
+  * clarify that padding only applies to in-place transforms
+
+    M ./doc/tutorial.texi -5 +10
+
+Sun Oct 28 18:42:48 EDT 2012  athena@fftw.org
+  * make the index-computation logic less paranoid
+
+  The problem is that for each K and for each expression of the form P[I
+  + STRIDE * K] in a loop, most compilers will try to lift an induction
+  variable PK := &P[I + STRIDE * K].  In large codelets we have many
+  such values of K.  For example, a codelet of size 32 with 4 input
+  pointers will generate O(128) induction variables, which will likely
+  overflow the register set, which is likely worse than doing the index
+  computation in the first place.
+
+  In the past we (wisely and correctly) assumed that compilers will do
+  the wrong thing, and consequently we disabled the induction-variable
+  "optimization" altogether by setting STRIDE ^= ZERO, where ZERO is a
+  value guaranteed to be 0.  Since the compiler does not know that
+  ZERO=0, it cannot perform its "optimization" and it is forced to
+  behave sensibly.
+
+  With this patch, FFTW is a little bit less paranoid.  FFTW now
+  disables the induction-variable optimization" only when we estimate
+  that the codelet uses more than ESTIMATED_AVAILABLE_INDEX_REGISTERS
+  induction variables.
+
+  Currently we set ESTIMATED_AVAILABLE_INDEX_REGISTERS=16.  16 registers ought
+  to be enough for anybody (or so the amd64 and ARM ISA's seem to imply).
+
+
+    M ./genfft/gen_hc2c.ml -1 +1
+    M ./genfft/gen_hc2cdft.ml -1 +1
+    M ./genfft/gen_hc2cdft_c.ml -1 +1
+    M ./genfft/gen_hc2hc.ml -1 +1
+    M ./genfft/gen_notw.ml -2 +2
+    M ./genfft/gen_notw_c.ml -2 +2
+    M ./genfft/gen_r2cb.ml -3 +3
+    M ./genfft/gen_r2cf.ml -3 +3
+    M ./genfft/gen_r2r.ml -2 +2
+    M ./genfft/gen_twiddle.ml -1 +1
+    M ./genfft/gen_twiddle_c.ml -1 +1
+    M ./genfft/gen_twidsq.ml -2 +2
+    M ./genfft/gen_twidsq_c.ml -2 +2
+    M ./genfft/genutil.ml -1 +2
+    M ./kernel/ifftw.h -3 +20
+
+Sun Oct 28 18:33:24 EDT 2012  athena@fftw.org
+  * silence warnings
+
+    M ./kernel/buffered.c +1
+    M ./rdft/rank0.c +1
+
+Sat Oct 27 09:58:49 EDT 2012  athena@fftw.org
+  * bump version to 3.3.3
+
+    M ./NEWS +7
+    M ./configure.ac -1 +1
+
+Sat Oct 27 09:55:15 EDT 2012  athena@fftw.org
+  * evaluate plans for >1ms when using gettimeofday()
+
+  The previous limit 10ms was too paranoid, and it made life difficult
+  on machines without an "official" cycle counter, such as ARM.
+
+    M ./kernel/timer.c -1 +1
+
+Sat Oct 27 09:46:04 EDT 2012  athena@fftw.org
+  * use 4-way NEON SIMD instead of 2-way
+
+  Kai-Uwe Bloem tried to warn me a year ago that 128-bit NEON was better
+  than 64-bit NEON even on machines with a 64-bit pipe, but I foolishly
+  did not listen.  Now that 128-bit NEON pipes are starting to appear on
+  the market it is definitely time to switch.
+
+
+    M ./simd-support/simd-neon.h -55 +100
+
+Wed Sep 26 14:21:12 EDT 2012  athena@fftw.org
+  * Note that fftw-3.3 includes MPI support
+
+    M ./doc/intro.texi -5 +4
+
+Wed Jul 18 11:25:40 EDT 2012  athena@fftw.org
+  * remove obsolete unused function
+
+    M ./dft/bluestein.c -14
+
+Fri Jun 29 15:57:14 EDT 2012  stevenj@fftw.org
+  * whoops, call omp_get_max_threads; thanks to Hanno Rein for the bug report
+
+    M ./doc/threads.texi -1 +1
+
 Sat Apr 28 10:55:09 EDT 2012  athena@fftw.org
   * Fix libfftw3/libfftw3_threads chicken-egg problem
 

Makefile.in

@@ -1,4 +1,4 @@
-# Makefile.in generated by automake 1.11.3 from Makefile.am.
+# Makefile.in generated by automake 1.11.6 from Makefile.am.
 # @configure_input@
 
 # Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
@@ -17,6 +17,23 @@
 
 
 VPATH = @srcdir@
+am__make_dryrun = \
+  { \
+    am__dry=no; \
+    case $$MAKEFLAGS in \
+      *\\[\ \	]*) \
+        echo 'am--echo: ; @echo "AM"  OK' | $(MAKE) -f - 2>/dev/null \
+          | grep '^AM OK$$' >/dev/null || am__dry=yes;; \
+      *) \
+        for am__flg in $$MAKEFLAGS; do \
+          case $$am__flg in \
+            *=*|--*) ;; \
+            *n*) am__dry=yes; break;; \
+          esac; \
+        done;; \
+    esac; \
+    test $$am__dry = yes; \
+  }
 pkgdatadir = $(datadir)/@PACKAGE@
 pkgincludedir = $(includedir)/@PACKAGE@
 pkglibdir = $(libdir)/@PACKAGE@
@@ -124,6 +141,11 @@ RECURSIVE_TARGETS = all-recursive check-recursive dvi-recursive \
 	install-pdf-recursive install-ps-recursive install-recursive \
 	installcheck-recursive installdirs-recursive pdf-recursive \
 	ps-recursive uninstall-recursive
+am__can_run_installinfo = \
+  case $$AM_UPDATE_INFO_DIR in \
+    n|no|NO) false;; \
+    *) (install-info --version) >/dev/null 2>&1;; \
+  esac
 DATA = $(pkgconfig_DATA)
 RECURSIVE_CLEAN_TARGETS = mostlyclean-recursive clean-recursive	\
   distclean-recursive maintainer-clean-recursive
@@ -447,14 +469,15 @@ fftw.pc: $(top_builddir)/config.status $(srcdir)/fftw.pc.in
 	cd $(top_builddir) && $(SHELL) ./config.status $@
 install-libLTLIBRARIES: $(lib_LTLIBRARIES)
 	@$(NORMAL_INSTALL)
-	test -z "$(libdir)" || $(MKDIR_P) "$(DESTDIR)$(libdir)"
 	@list='$(lib_LTLIBRARIES)'; test -n "$(libdir)" || list=; \
 	list2=; for p in $$list; do \
 	  if test -f $$p; then \
 	    list2="$$list2 $$p"; \
 	  else :; fi; \
 	done; \
 	test -z "$$list2" || { \
+	  echo " $(MKDIR_P) '$(DESTDIR)$(libdir)'"; \
+	  $(MKDIR_P) "$(DESTDIR)$(libdir)" || exit 1; \
 	  echo " $(LIBTOOL) $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=install $(INSTALL) $(INSTALL_STRIP_FLAG) $$list2 '$(DESTDIR)$(libdir)'"; \
 	  $(LIBTOOL) $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=install $(INSTALL) $(INSTALL_STRIP_FLAG) $$list2 "$(DESTDIR)$(libdir)"; \
 	}
@@ -495,8 +518,11 @@ distclean-libtool:
 	-rm -f libtool config.lt
 install-pkgconfigDATA: $(pkgconfig_DATA)
 	@$(NORMAL_INSTALL)
-	test -z "$(pkgconfigdir)" || $(MKDIR_P) "$(DESTDIR)$(pkgconfigdir)"
 	@list='$(pkgconfig_DATA)'; test -n "$(pkgconfigdir)" || list=; \
+	if test -n "$$list"; then \
+	  echo " $(MKDIR_P) '$(DESTDIR)$(pkgconfigdir)'"; \
+	  $(MKDIR_P) "$(DESTDIR)$(pkgconfigdir)" || exit 1; \
+	fi; \
 	for p in $$list; do \
 	  if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \
 	  echo "$$d$$p"; \
@@ -681,13 +707,10 @@ distdir: $(DISTFILES)
 	done
 	@list='$(DIST_SUBDIRS)'; for subdir in $$list; do \
 	  if test "$$subdir" = .; then :; else \
-	    test -d "$(distdir)/$$subdir" \
-	    || $(MKDIR_P) "$(distdir)/$$subdir" \
-	    || exit 1; \
-	  fi; \
-	done
-	@list='$(DIST_SUBDIRS)'; for subdir in $$list; do \
-	  if test "$$subdir" = .; then :; else \
+	    $(am__make_dryrun) \
+	      || test -d "$(distdir)/$$subdir" \
+	      || $(MKDIR_P) "$(distdir)/$$subdir" \
+	      || exit 1; \
 	    dir1=$$subdir; dir2="$(distdir)/$$subdir"; \
 	    $(am__relativize); \
 	    new_distdir=$$reldir; \
@@ -773,7 +796,7 @@ distcheck: dist
 	*.zip*) \
 	  unzip $(distdir).zip ;;\
 	esac
-	chmod -R a-w $(distdir); chmod a+w $(distdir)
+	chmod -R a-w $(distdir); chmod u+w $(distdir)
 	mkdir $(distdir)/_build
 	mkdir $(distdir)/_inst
 	chmod a-w $(distdir)

NEWS

@@ -1,3 +1,15 @@
+FFTW 3.3.3
+
+* Fix deadlock bug in MPI transforms (thanks to Michael Pippig for the
+  bug report and patch, and to Graham Dennis for the bug report).
+
+* Use 128-bit ARM NEON instructions instead of 64-bits.  This change
+  appears to speed up even ARM processors with a 64-bit NEON pipe.
+
+* Speed improvements for single-precision AVX.
+
+* Speed up planner on machines without "official" cycle counters, such as ARM.
+
 FFTW 3.3.2
 
 * Removed an archaic stack-alignment hack that was failing with

aclocal.m4

@@ -1,4 +1,4 @@
-# generated automatically by aclocal 1.11.3 -*- Autoconf -*-
+# generated automatically by aclocal 1.11.6 -*- Autoconf -*-
 
 # Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
 # 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
@@ -14,8 +14,8 @@
 
 m4_ifndef([AC_AUTOCONF_VERSION],
   [m4_copy([m4_PACKAGE_VERSION], [AC_AUTOCONF_VERSION])])dnl
-m4_if(m4_defn([AC_AUTOCONF_VERSION]), [2.68],,
-[m4_warning([this file was generated for autoconf 2.68.
+m4_if(m4_defn([AC_AUTOCONF_VERSION]), [2.69],,
+[m4_warning([this file was generated for autoconf 2.69.
 You have another version of autoconf.  It may work, but is not guaranteed to.
 If you have problems, you may need to regenerate the build system entirely.
 To do so, use the procedure documented by the package, typically `autoreconf'.])])
@@ -38,7 +38,7 @@ AC_DEFUN([AM_AUTOMAKE_VERSION],
 [am__api_version='1.11'
 dnl Some users find AM_AUTOMAKE_VERSION and mistake it for a way to
 dnl require some minimum version.  Point them to the right macro.
-m4_if([$1], [1.11.3], [],
+m4_if([$1], [1.11.6], [],
       [AC_FATAL([Do not call $0, use AM_INIT_AUTOMAKE([$1]).])])dnl
 ])
 
@@ -54,7 +54,7 @@ m4_define([_AM_AUTOCONF_VERSION], [])
 # Call AM_AUTOMAKE_VERSION and AM_AUTOMAKE_VERSION so they can be traced.
 # This function is AC_REQUIREd by AM_INIT_AUTOMAKE.
 AC_DEFUN([AM_SET_CURRENT_AUTOMAKE_VERSION],
-[AM_AUTOMAKE_VERSION([1.11.3])dnl
+[AM_AUTOMAKE_VERSION([1.11.6])dnl
 m4_ifndef([AC_AUTOCONF_VERSION],
   [m4_copy([m4_PACKAGE_VERSION], [AC_AUTOCONF_VERSION])])dnl
 _AM_AUTOCONF_VERSION(m4_defn([AC_AUTOCONF_VERSION]))])

api/Makefile.in

@@ -1,4 +1,4 @@
-# Makefile.in generated by automake 1.11.3 from Makefile.am.
+# Makefile.in generated by automake 1.11.6 from Makefile.am.
 # @configure_input@
 
 # Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
@@ -17,6 +17,23 @@
 
 
 VPATH = @srcdir@
+am__make_dryrun = \
+  { \
+    am__dry=no; \
+    case $$MAKEFLAGS in \
+      *\\[\ \	]*) \
+        echo 'am--echo: ; @echo "AM"  OK' | $(MAKE) -f - 2>/dev/null \
+          | grep '^AM OK$$' >/dev/null || am__dry=yes;; \
+      *) \
+        for am__flg in $$MAKEFLAGS; do \
+          case $$am__flg in \
+            *=*|--*) ;; \
+            *n*) am__dry=yes; break;; \
+          esac; \
+        done;; \
+    esac; \
+    test $$am__dry = yes; \
+  }
 pkgdatadir = $(datadir)/@PACKAGE@
 pkgincludedir = $(includedir)/@PACKAGE@
 pkglibdir = $(libdir)/@PACKAGE@
@@ -97,6 +114,11 @@ LINK = $(LIBTOOL) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) \
 	$(LDFLAGS) -o $@
 SOURCES = $(libapi_la_SOURCES)
 DIST_SOURCES = $(libapi_la_SOURCES)
+am__can_run_installinfo = \
+  case $$AM_UPDATE_INFO_DIR in \
+    n|no|NO) false;; \
+    *) (install-info --version) >/dev/null 2>&1;; \
+  esac
 am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`;
 am__vpath_adj = case $$p in \
     $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \
@@ -455,8 +477,11 @@ clean-libtool:
 	-rm -rf .libs _libs
 install-includeHEADERS: $(include_HEADERS)
 	@$(NORMAL_INSTALL)
-	test -z "$(includedir)" || $(MKDIR_P) "$(DESTDIR)$(includedir)"
 	@list='$(include_HEADERS)'; test -n "$(includedir)" || list=; \
+	if test -n "$$list"; then \
+	  echo " $(MKDIR_P) '$(DESTDIR)$(includedir)'"; \
+	  $(MKDIR_P) "$(DESTDIR)$(includedir)" || exit 1; \
+	fi; \
 	for p in $$list; do \
 	  if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \
 	  echo "$$d$$p"; \
@@ -473,8 +498,11 @@ uninstall-includeHEADERS:
 	dir='$(DESTDIR)$(includedir)'; $(am__uninstall_files_from_dir)
 install-nodist_includeHEADERS: $(nodist_include_HEADERS)
 	@$(NORMAL_INSTALL)
-	test -z "$(includedir)" || $(MKDIR_P) "$(DESTDIR)$(includedir)"
 	@list='$(nodist_include_HEADERS)'; test -n "$(includedir)" || list=; \
+	if test -n "$$list"; then \
+	  echo " $(MKDIR_P) '$(DESTDIR)$(includedir)'"; \
+	  $(MKDIR_P) "$(DESTDIR)$(includedir)" || exit 1; \
+	fi; \
 	for p in $$list; do \
 	  if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \
 	  echo "$$d$$p"; \