From patchwork Thu Feb 7 15:51:10 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [ARM,3/3] Add vectorization support for rounding functions From: Kyrylo Tkachov X-Patchwork-Id: 218942 Message-Id: <006c01ce054a$f390e080$dab2a180$@tkachov@arm.com> To: Cc: "Ramana Radhakrishnan" , "Richard Earnshaw" Date: Thu, 7 Feb 2013 15:51:10 -0000 Hi all, This testsuite patch has been okayed at http://gcc.gnu.org/ml/gcc-patches/2012-12/msg01141.html but I have not applied it and I'd like to add a couple of things to it. Currently, add_options_for_arm_v8_neon would explicitly set -mfloat-abi=softfp which would break check_effective_target_arm_v8_neon_hw for configurations with hard float ABI, thus preventing the execution tests that use this check in gcc.dg/vect from running. This patch fixes that. Ok to put it in with the other two ARM rounding vectorization patches that have been okayed for stage1? Thanks, Kyrill gcc/testuite/ChangeLog 2013-02-07 Kyrylo Tkachov * lib/target-supports.exp (check_effective_target_arm_v8_neon_hw): New procedure. (check_effective_target_arm_v8_neon_ok_nocache): Likewise. (check_effective_target_arm_v8_neon_ok): Change to use check_effective_target_arm_v8_neon_ok_nocache. (add_options_for_arm_v8_neon): Use et_arm_v8_neon_flags to set ARMv8 NEON flags. (check_effective_target_vect_call_btruncf): Enable for arm and ARMv8 NEON. (check_effective_target_vect_call_ceilf): Likewise. (check_effective_target_vect_call_floorf): Likewise. (check_effective_target_vect_call_roundf): Likewise. (check_vect_support_and_set_flags): Handle ARMv8 NEON effective target. > -----Original Message----- > From: gcc-patches-owner@gcc.gnu.org [mailto:gcc-patches- > owner@gcc.gnu.org] On Behalf Of Kyrylo Tkachov > Sent: 18 December 2012 13:34 > To: gcc-patches@gcc.gnu.org > Cc: Ramana Radhakrishnan; Richard Earnshaw > Subject: [PATCH][ARM][3/3] Add vectorization support for rounding > functions > > Hi all, > This patch adds arm and v8 NEON to the effective target checks that are > used > in the rounding functions vectorisation tests. > A new effective target check for NEON hardware is added This check is > used > to determine > whether to do runtime tests or just compilation. > > With these changes the following tests now PASS on arm instead of being > UNSUPPORTED: > * gcc.dg/vect/vect-rounding-btrunc.c > * gcc.dg/vect/vect-rounding-ceilf.c > * gcc.dg/vect/vect-rounding-floorf.c > * gcc.dg/vect/vect-rounding-roundf.c > > Tested on arm-none-eabi with model and softfp float ABI. > > Ok for trunk? > > Thanks, > Kyrill > > gcc/testuite/ChangeLog > > 2012-12-18 Kyrylo Tkachov > > * lib/target-supports.exp > (check_effective_target_arm_v8_neon_hw): > New procedure. > (check_effective_target_vect_call_btruncf): > Add check for arm and ARMv8 NEON. > (check_effective_target_vect_call_ceilf): Likewise. > (check_effective_target_vect_call_floorf): Likewise. > (check_effective_target_vect_call_roundf): Likewise. > (check_vect_support_and_set_flags): Handle ARMv8 NEON effective > target. diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index 0c824b8..3158e87 100644 --- a/gcc/testsuite/lib/target-supports.exp +++ b/gcc/testsuite/lib/target-supports.exp @@ -2147,22 +2147,6 @@ proc check_effective_target_arm_v8_vfp_ok {} { } } -# Return 1 if this is an ARM target supporting -mfpu=neon-fp-armv8 -# -mfloat-abi=softfp -proc check_effective_target_arm_v8_neon_ok {} { - if { [check_effective_target_arm32] } { - return [check_no_compiler_messages arm_v8_neon_ok object { - int foo (void) - { - __asm__ volatile ("vrintn.f32 q0, q0"); - return 0; - } - } "-mfpu=neon-fp-armv8 -mfloat-abi=softfp"] - } else { - return 0 - } -} - # Return 1 if this is an ARM target supporting -mfpu=vfp # -mfloat-abi=hard. Some multilibs may be incompatible with these # options. @@ -2226,7 +2210,8 @@ proc add_options_for_arm_v8_neon { flags } { if { ! [check_effective_target_arm_v8_neon_ok] } { return "$flags" } - return "$flags -march=armv8-a -mfpu=neon-fp-armv8 -mfloat-abi=softfp" + global et_arm_v8_neon_flags + return "$flags $et_arm_v8_neon_flags" } # Add the options needed for NEON. We need either -mfloat-abi=softfp @@ -2270,6 +2255,38 @@ proc check_effective_target_arm_neon_ok { } { check_effective_target_arm_neon_ok_nocache] } +# Return 1 if this is an ARM target supporting -mfpu=neon-fp-armv8 +# -mfloat-abi=softfp or equivalent options. Some multilibs may be +# incompatible with these options. Also set et_arm_v8_neon_flags to the +# best options to add. + +proc check_effective_target_arm_v8_neon_ok_nocache { } { + global et_arm_v8_neon_flags + set et_arm_v8_neon_flags "" + if { [check_effective_target_arm32] } { + foreach flags {"" "-mfloat-abi=softfp" "-mfpu=neon-fp-armv8" "-mfpu=neon-fp-armv8 -mfloat-abi=softfp"} { + if { [check_no_compiler_messages_nocache arm_v8_neon_ok object { + #include "arm_neon.h" + void + foo () + { + __asm__ volatile ("vrintn.f32 q0, q0"); + } + } "$flags"] } { + set et_arm_v8_neon_flags $flags + return 1 + } + } + } + + return 0 +} + +proc check_effective_target_arm_v8_neon_ok { } { + return [check_cached_effective_target arm_v8_neon_ok \ + check_effective_target_arm_v8_neon_ok_nocache] +} + # Return 1 if this is an ARM target supporting -mfpu=neon-vfpv4 # -mfloat-abi=softfp or equivalent options. Some multilibs may be # incompatible with these options. Also set et_arm_neonv2_flags to the @@ -2509,6 +2526,24 @@ proc check_effective_target_arm_neonv2_hw { } { } [add_options_for_arm_neonv2 ""]] } +# Return 1 if the target supports executing ARMv8 NEON instructions, 0 +# otherwise. + +proc check_effective_target_arm_v8_neon_hw { } { + return [check_runtime arm_v8_neon_hw_available { + #include "arm_neon.h" + int + main (void) + { + float32x2_t a; + asm ("vrinta.f32 %P0, %P1" + : "=w" (a) + : "0" (a)); + return 0; + } + } [add_options_for_arm_v8_neon ""]] +} + # Return 1 if this is a ARM target with NEON enabled. proc check_effective_target_arm_neon { } { @@ -4035,7 +4070,9 @@ proc check_effective_target_vect_call_btruncf { } { verbose "check_effective_target_vect_call_btruncf: using cached result" 2 } else { set et_vect_call_btruncf_saved 0 - if { [istarget aarch64*-*-*] } { + if { [istarget aarch64*-*-*] + || ([istarget arm*-*-*] + && [check_effective_target_arm_v8_neon_ok]) } { set et_vect_call_btruncf_saved 1 } } @@ -4071,7 +4108,9 @@ proc check_effective_target_vect_call_ceilf { } { verbose "check_effective_target_vect_call_ceilf: using cached result" 2 } else { set et_vect_call_ceilf_saved 0 - if { [istarget aarch64*-*-*] } { + if { [istarget aarch64*-*-*] + || ([istarget arm*-*-*] + && [check_effective_target_arm_v8_neon_ok]) } { set et_vect_call_ceilf_saved 1 } } @@ -4107,7 +4146,9 @@ proc check_effective_target_vect_call_floorf { } { verbose "check_effective_target_vect_call_floorf: using cached result" 2 } else { set et_vect_call_floorf_saved 0 - if { [istarget aarch64*-*-*] } { + if { [istarget aarch64*-*-*] + || ([istarget arm*-*-*] + && [check_effective_target_arm_v8_neon_ok]) } { set et_vect_call_floorf_saved 1 } } @@ -4215,7 +4256,9 @@ proc check_effective_target_vect_call_roundf { } { verbose "check_effective_target_vect_call_roundf: using cached result" 2 } else { set et_vect_call_roundf_saved 0 - if { [istarget aarch64*-*-*] } { + if { [istarget aarch64*-*-*] + || ([istarget arm*-*-*] + && [check_effective_target_arm_v8_neon_ok]) } { set et_vect_call_roundf_saved 1 } } @@ -5117,6 +5160,14 @@ proc check_vect_support_and_set_flags { } { } } elseif [istarget ia64-*-*] { set dg-do-what-default run + } elseif [is-effective-target arm_v8_neon_ok] { + eval lappend DEFAULT_VECTCFLAGS [add_options_for_arm_v8_neon ""] + lappend DEFAULT_VECTCFLAGS "-ffast-math" + if [is-effective-target arm_v8_neon_hw] { + set dg-do-what-default run + } else { + set dg-do-what-default compile + } } elseif [is-effective-target arm_neon_ok] { eval lappend DEFAULT_VECTCFLAGS [add_options_for_arm_neon ""] # NEON does not support denormals, so is not used for vectorization by