Hi, this patch contains changes to the configuration mechanism and offload bits, so that users can build compilers with HSA support.
It is a re-post of https://gcc.gnu.org/ml/gcc-patches/2015-12/msg00714.html, which, has already been approved by Jakub after a few changes (https://gcc.gnu.org/ml/gcc-patches/2015-12/msg01284.html). thanks, Martin 2016-01-13 Martin Jambor <mjam...@suse.cz> * Makefile.in (OBJS): Add new source files. (GTFILES): Add hsa.c. * common.opt (disable_hsa): New variable. (-Whsa): New warning. * config.in (ENABLE_HSA): New. * configure.ac: Treat hsa differently from other accelerators. (OFFLOAD_TARGETS): Define ENABLE_OFFLOADING according to $enable_offloading. (ENABLE_HSA): Define ENABLE_HSA according to $enable_hsa. * doc/install.texi (Configuration): Document --with-hsa-runtime, --with-hsa-runtime-include, --with-hsa-runtime-lib and --with-hsa-kmt-lib. * doc/invoke.texi (-Whsa): Document. (hsa-gen-debug-stores): Likewise. * lto-wrapper.c (compile_images_for_offload_targets): Do not attempt to invoke offload compiler for hsa acclerator. * opts.c (common_handle_option): Determine whether HSA offloading should be performed. * params.def (PARAM_HSA_GEN_DEBUG_STORES): New parameter. libgomp/plugin/ * Makefrag.am: Add HSA plugin requirements. * configfrag.ac (HSA_RUNTIME_INCLUDE): New variable. (HSA_RUNTIME_LIB): Likewise. (HSA_RUNTIME_CPPFLAGS): Likewise. (HSA_RUNTIME_INCLUDE): New substitution. (HSA_RUNTIME_LIB): Likewise. (HSA_RUNTIME_LDFLAGS): Likewise. (hsa-runtime): New configure option. (hsa-runtime-include): Likewise. (hsa-runtime-lib): Likewise. (PLUGIN_HSA): New substitution variable. Fill HSA_RUNTIME_INCLUDE and HSA_RUNTIME_LIB according to the new configure options. (PLUGIN_HSA_CPPFLAGS): Likewise. (PLUGIN_HSA_LDFLAGS): Likewise. (PLUGIN_HSA_LIBS): Likewise. Check that we have access to HSA run-time. diff --git a/gcc/Makefile.in b/gcc/Makefile.in index 44a18eb..ab9cbbf 100644 --- a/gcc/Makefile.in +++ b/gcc/Makefile.in @@ -1297,6 +1297,11 @@ OBJS = \ graphite-sese-to-poly.o \ gtype-desc.o \ haifa-sched.o \ + hsa.o \ + hsa-gen.o \ + hsa-regalloc.o \ + hsa-brig.o \ + hsa-dump.o \ hw-doloop.o \ hwint.o \ ifcvt.o \ @@ -1321,6 +1326,7 @@ OBJS = \ ipa-icf.o \ ipa-icf-gimple.o \ ipa-reference.o \ + ipa-hsa.o \ ipa-ref.o \ ipa-utils.o \ ipa.o \ @@ -2404,6 +2410,7 @@ GTFILES = $(CPP_ID_DATA_H) $(srcdir)/input.h $(srcdir)/coretypes.h \ $(srcdir)/sancov.c \ $(srcdir)/ipa-devirt.c \ $(srcdir)/internal-fn.h \ + $(srcdir)/hsa.c \ @all_gtfiles@ # Compute the list of GT header files from the corresponding C sources, diff --git a/gcc/common.opt b/gcc/common.opt index 49d347c..23e6ed7 100644 --- a/gcc/common.opt +++ b/gcc/common.opt @@ -239,6 +239,10 @@ Inserts call to __sanitizer_cov_trace_pc into every basic block. Variable bool dump_base_name_prefixed = false +; Flag whether HSA generation has been explicitely disabled +Variable +bool flag_disable_hsa = false + ### Driver @@ -593,6 +597,10 @@ Wfree-nonheap-object Common Var(warn_free_nonheap_object) Init(1) Warning Warn when attempting to free a non-heap object. +Whsa +Common Var(warn_hsa) Init(1) Warning +Warn when a function cannot be expanded to HSAIL. + Winline Common Var(warn_inline) Warning Warn when an inlined function cannot be inlined. diff --git a/gcc/config.in b/gcc/config.in index c00cd0f..c3340bb0 100644 --- a/gcc/config.in +++ b/gcc/config.in @@ -144,6 +144,12 @@ #endif +/* Define this to enable support for generating HSAIL. */ +#ifndef USED_FOR_TARGET +#undef ENABLE_HSA +#endif + + /* Define if gcc should always pass --build-id to linker. */ #ifndef USED_FOR_TARGET #undef ENABLE_LD_BUILDID diff --git a/gcc/configure.ac b/gcc/configure.ac index 0a626e9..8d3a869 100644 --- a/gcc/configure.ac +++ b/gcc/configure.ac @@ -940,6 +940,13 @@ AC_SUBST(accel_dir_suffix) for tgt in `echo $enable_offload_targets | sed 's/,/ /g'`; do tgt=`echo $tgt | sed 's/=.*//'` + + if echo "$tgt" | grep "^hsa" > /dev/null ; then + enable_hsa=1 + else + enable_offloading=1 + fi + if test x"$offload_targets" = x; then offload_targets=$tgt else @@ -948,7 +955,7 @@ for tgt in `echo $enable_offload_targets | sed 's/,/ /g'`; do done AC_DEFINE_UNQUOTED(OFFLOAD_TARGETS, "$offload_targets", [Define to offload targets, separated by commas.]) -if test x"$offload_targets" != x; then +if test x"$enable_offloading" != x; then AC_DEFINE(ENABLE_OFFLOADING, 1, [Define this to enable support for offloading.]) else @@ -956,6 +963,11 @@ else [Define this to enable support for offloading.]) fi +if test x"$enable_hsa" = x1 ; then + AC_DEFINE(ENABLE_HSA, 1, + [Define this to enable support for generating HSAIL.]) +fi + AC_ARG_WITH(multilib-list, [AS_HELP_STRING([--with-multilib-list], [select multilibs (AArch64, SH and x86-64 only)])], :, diff --git a/gcc/doc/install.texi b/gcc/doc/install.texi index 1c2b702..062f42c 100644 --- a/gcc/doc/install.texi +++ b/gcc/doc/install.texi @@ -1992,6 +1992,28 @@ specifying paths @var{path1}, @dots{}, @var{pathN}. % @var{srcdir}/configure \ --enable-offload-target=i686-unknown-linux-gnu=/path/to/i686/compiler,x86_64-pc-linux-gnu @end smallexample + +If @samp{hsa} is specified as one of the targets, the compiler will be +built with support for HSA GPU accelerators. Because the same +compiler will emit the accelerator code, no path should be specified. + +@item --with-hsa-runtime=@var{pathname} +@itemx --with-hsa-runtime-include=@var{pathname} +@itemx --with-hsa-runtime-lib=@var{pathname} + +If you configure GCC with HSA offloading but do not have the HSA +run-time library installed in a standard location then you can +explicitly specify the directory where they are installed. The +@option{--with-hsa-runtime=@/@var{hsainstalldir}} option is a +shorthand for +@option{--with-hsa-runtime-lib=@/@var{hsainstalldir}/lib} and +@option{--with-hsa-runtime-include=@/@var{hsainstalldir}/include}. + +@item --with-hsa-kmt-lib=@var{pathname} + +If you configure GCC with HSA offloading but do not have the HSA +KMT library installed in a standard location then you can +explicitly specify the directory where it resides. @end table @subheading Cross-Compiler-Specific Options diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi index 77115a7..8ce04b1 100644 --- a/gcc/doc/invoke.texi +++ b/gcc/doc/invoke.texi @@ -295,7 +295,7 @@ Objective-C and Objective-C++ Dialects}. -Wunused-but-set-parameter -Wunused-but-set-variable @gol -Wuseless-cast -Wvariadic-macros -Wvector-operation-performance @gol -Wvla -Wvolatile-register-var -Wwrite-strings @gol --Wzero-as-null-pointer-constant} +-Wzero-as-null-pointer-constant -Whsa} @item C and Objective-C-only Warning Options @gccoptlist{-Wbad-function-cast -Wmissing-declarations @gol @@ -5721,6 +5721,10 @@ Suppress warnings when a positional initializer is used to initialize a structure that has been marked with the @code{designated_init} attribute. +@item -Whsa +Issue a warning when HSAIL cannot be emitted for the compiled function or +OpenMP construct. + @end table @node Debugging Options @@ -11262,6 +11266,12 @@ dynamic, guided, auto, runtime). The default is static. Maximum depth of recursion when querying properties of SSA names in things like fold routines. One level of recursion corresponds to following a use-def chain. + +@item hsa-gen-debug-stores +Enable emission of special debug stores within HSA kernels which are +then read and reported by libgomp plugin. Generation of these stores +is disabled by default, use @option{--param hsa-gen-debug-stores=1} to +enable it. @end table @end table diff --git a/gcc/lto-wrapper.c b/gcc/lto-wrapper.c index ecb9996..16d1f45 100644 --- a/gcc/lto-wrapper.c +++ b/gcc/lto-wrapper.c @@ -736,6 +736,7 @@ compile_images_for_offload_targets (unsigned in_argc, char *in_argv[], return; unsigned num_targets = parse_env_var (target_names, &names, NULL); + int next_name_entry = 0; const char *compiler_path = getenv ("COMPILER_PATH"); if (!compiler_path) goto out; @@ -745,13 +746,19 @@ compile_images_for_offload_targets (unsigned in_argc, char *in_argv[], offload_names = XCNEWVEC (char *, num_targets + 1); for (unsigned i = 0; i < num_targets; i++) { - offload_names[i] + /* HSA does not use LTO-like streaming and a different compiler, skip + it. */ + if (strcmp (names[i], "hsa") == 0) + continue; + + offload_names[next_name_entry] = compile_offload_image (names[i], compiler_path, in_argc, in_argv, compiler_opts, compiler_opt_count, linker_opts, linker_opt_count); - if (!offload_names[i]) + if (!offload_names[next_name_entry]) fatal_error (input_location, "problem with building target image for %s\n", names[i]); + next_name_entry++; } out: diff --git a/gcc/opts.c b/gcc/opts.c index 2add158..8e8410c 100644 --- a/gcc/opts.c +++ b/gcc/opts.c @@ -1916,8 +1916,35 @@ common_handle_option (struct gcc_options *opts, break; case OPT_foffload_: - /* Deferred. */ - break; + { + const char *p = arg; + opts->x_flag_disable_hsa = true; + while (*p != 0) + { + const char *comma = strchr (p, ','); + + if ((strncmp (p, "disable", 7) == 0) + && (p[7] == ',' || p[7] == '\0')) + { + opts->x_flag_disable_hsa = true; + break; + } + + if ((strncmp (p, "hsa", 3) == 0) + && (p[3] == ',' || p[3] == '\0')) + { +#ifdef ENABLE_HSA + opts->x_flag_disable_hsa = false; +#else + sorry ("HSA has not been enabled during configuration"); +#endif + } + if (!comma) + break; + p = comma + 1; + } + break; + } #ifndef ACCEL_COMPILER case OPT_foffload_abi_: diff --git a/gcc/params.def b/gcc/params.def index 308844a..88971c7 100644 --- a/gcc/params.def +++ b/gcc/params.def @@ -1183,6 +1183,11 @@ DEFPARAM (PARAM_MAX_RTL_IF_CONVERSION_INSNS, "Maximum number of insns in a basic block to consider for RTL " "if-conversion.", 10, 0, 99) + +DEFPARAM (PARAM_HSA_GEN_DEBUG_STORES, + "hsa-gen-debug-stores", + "Level of hsa debug stores verbosity", + 0, 0, 1) /* Local variables: diff --git a/libgomp/plugin/Makefrag.am b/libgomp/plugin/Makefrag.am index 4efe963..035a663 100644 --- a/libgomp/plugin/Makefrag.am +++ b/libgomp/plugin/Makefrag.am @@ -38,3 +38,16 @@ libgomp_plugin_nvptx_la_LDFLAGS += $(PLUGIN_NVPTX_LDFLAGS) libgomp_plugin_nvptx_la_LIBADD = libgomp.la $(PLUGIN_NVPTX_LIBS) libgomp_plugin_nvptx_la_LIBTOOLFLAGS = --tag=disable-static endif + +if PLUGIN_HSA +# Heterogenous Systems Architecture plugin +libgomp_plugin_hsa_version_info = -version-info $(libtool_VERSION) +toolexeclib_LTLIBRARIES += libgomp-plugin-hsa.la +libgomp_plugin_hsa_la_SOURCES = plugin/plugin-hsa.c +libgomp_plugin_hsa_la_CPPFLAGS = $(AM_CPPFLAGS) $(PLUGIN_HSA_CPPFLAGS) +libgomp_plugin_hsa_la_LDFLAGS = $(libgomp_plugin_hsa_version_info) \ + $(lt_host_flags) +libgomp_plugin_hsa_la_LDFLAGS += $(PLUGIN_HSA_LDFLAGS) +libgomp_plugin_hsa_la_LIBADD = libgomp.la $(PLUGIN_HSA_LIBS) +libgomp_plugin_hsa_la_LIBTOOLFLAGS = --tag=disable-static +endif diff --git a/libgomp/plugin/configfrag.ac b/libgomp/plugin/configfrag.ac index 768954a..2a9d9f9 100644 --- a/libgomp/plugin/configfrag.ac +++ b/libgomp/plugin/configfrag.ac @@ -81,6 +81,62 @@ AC_SUBST(PLUGIN_NVPTX_CPPFLAGS) AC_SUBST(PLUGIN_NVPTX_LDFLAGS) AC_SUBST(PLUGIN_NVPTX_LIBS) +# Look for HSA run-time, its includes and libraries + +HSA_RUNTIME_INCLUDE= +HSA_RUNTIME_LIB= +AC_SUBST(HSA_RUNTIME_INCLUDE) +AC_SUBST(HSA_RUNTIME_LIB) +HSA_RUNTIME_CPPFLAGS= +HSA_RUNTIME_LDFLAGS= + +AC_ARG_WITH(hsa-runtime, + [AS_HELP_STRING([--with-hsa-runtime=PATH], + [specify prefix directory for installed HSA run-time package. + Equivalent to --with-hsa-runtime-include=PATH/include + plus --with-hsa-runtime-lib=PATH/lib])]) +AC_ARG_WITH(hsa-runtime-include, + [AS_HELP_STRING([--with-hsa-runtime-include=PATH], + [specify directory for installed HSA run-time include files])]) +AC_ARG_WITH(hsa-runtime-lib, + [AS_HELP_STRING([--with-hsa-runtime-lib=PATH], + [specify directory for the installed HSA run-time library])]) +if test "x$with_hsa_runtime" != x; then + HSA_RUNTIME_INCLUDE=$with_hsa_runtime/include + HSA_RUNTIME_LIB=$with_hsa_runtime/lib +fi +if test "x$with_hsa_runtime_include" != x; then + HSA_RUNTIME_INCLUDE=$with_hsa_runtime_include +fi +if test "x$with_hsa_runtime_lib" != x; then + HSA_RUNTIME_LIB=$with_hsa_runtime_lib +fi +if test "x$HSA_RUNTIME_INCLUDE" != x; then + HSA_RUNTIME_CPPFLAGS=-I$HSA_RUNTIME_INCLUDE +fi +if test "x$HSA_RUNTIME_LIB" != x; then + HSA_RUNTIME_LDFLAGS=-L$HSA_RUNTIME_LIB +fi + +AC_ARG_WITH(hsa-kmt-lib, + [AS_HELP_STRING([--with-hsa-kmt-lib=PATH], + [specify directory for installed HSA KMT library.])]) +if test "x$with_hsa_kmt_lib" != x; then + HSA_RUNTIME_LDFLAGS="$HSA_RUNTIME_LDFLAGS -L$with_hsa_kmt_lib" + HSA_RUNTIME_LIB= +fi + +PLUGIN_HSA=0 +PLUGIN_HSA_CPPFLAGS= +PLUGIN_HSA_LDFLAGS= +PLUGIN_HSA_LIBS= +AC_SUBST(PLUGIN_HSA) +AC_SUBST(PLUGIN_HSA_CPPFLAGS) +AC_SUBST(PLUGIN_HSA_LDFLAGS) +AC_SUBST(PLUGIN_HSA_LIBS) + + + # Get offload targets and path to install tree of offloading compiler. offload_additional_options= offload_additional_lib_paths= @@ -122,6 +178,49 @@ if test x"$enable_offload_targets" != x; then ;; esac ;; + hsa*) + case "${target}" in + x86_64-*-*) + case " ${CC} ${CFLAGS} " in + *" -m32 "*) + PLUGIN_HSA=0 + ;; + *) + tgt_name=hsa + PLUGIN_HSA=$tgt + PLUGIN_HSA_CPPFLAGS=$HSA_RUNTIME_CPPFLAGS + PLUGIN_HSA_LDFLAGS=$HSA_RUNTIME_LDFLAGS + PLUGIN_HSA_LIBS="-lhsa-runtime64 -lhsakmt" + + PLUGIN_HSA_save_CPPFLAGS=$CPPFLAGS + CPPFLAGS="$PLUGIN_HSA_CPPFLAGS $CPPFLAGS" + PLUGIN_HSA_save_LDFLAGS=$LDFLAGS + LDFLAGS="$PLUGIN_HSA_LDFLAGS $LDFLAGS" + PLUGIN_HSA_save_LIBS=$LIBS + LIBS="$PLUGIN_HSA_LIBS $LIBS" + + AC_LINK_IFELSE( + [AC_LANG_PROGRAM( + [#include "hsa.h"], + [hsa_status_t status = hsa_init ()])], + [PLUGIN_HSA=1]) + CPPFLAGS=$PLUGIN_HSA_save_CPPFLAGS + LDFLAGS=$PLUGIN_HSA_save_LDFLAGS + LIBS=$PLUGIN_HSA_save_LIBS + case $PLUGIN_HSA in + hsa*) + HSA_PLUGIN=0 + AC_MSG_ERROR([HSA run-time package required for HSA support]) + ;; + esac + ;; + esac + ;; + *-*-*) + PLUGIN_HSA=0 + ;; + esac + ;; *) AC_MSG_ERROR([unknown offload target specified]) ;; @@ -145,3 +244,6 @@ AC_DEFINE_UNQUOTED(OFFLOAD_TARGETS, "$offload_targets", AM_CONDITIONAL([PLUGIN_NVPTX], [test $PLUGIN_NVPTX = 1]) AC_DEFINE_UNQUOTED([PLUGIN_NVPTX], [$PLUGIN_NVPTX], [Define to 1 if the NVIDIA plugin is built, 0 if not.]) +AM_CONDITIONAL([PLUGIN_HSA], [test $PLUGIN_HSA = 1]) +AC_DEFINE_UNQUOTED([PLUGIN_HSA], [$PLUGIN_HSA], + [Define to 1 if the HSA plugin is built, 0 if not.])
