From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id F0B07385800D; Fri, 16 Jul 2021 12:15:49 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org F0B07385800D From: "kastianoza at gmail dot com" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/101471] New: AVX512 incorrect writemask generated for _mm512_fpclass_ps_mask in O0 Date: Fri, 16 Jul 2021 12:15:49 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: new X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: gcc X-Bugzilla-Component: target X-Bugzilla-Version: 11.1.0 X-Bugzilla-Keywords: X-Bugzilla-Severity: normal X-Bugzilla-Who: kastianoza at gmail dot com X-Bugzilla-Status: UNCONFIRMED X-Bugzilla-Resolution: X-Bugzilla-Priority: P3 X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: bug_id short_desc product version bug_status bug_severity priority component assigned_to reporter target_milestone Message-ID: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: gcc-bugs@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gcc-bugs mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 16 Jul 2021 12:15:50 -0000 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D101471 Bug ID: 101471 Summary: AVX512 incorrect writemask generated for _mm512_fpclass_ps_mask in O0 Product: gcc Version: 11.1.0 Status: UNCONFIRMED Severity: normal Priority: P3 Component: target Assignee: unassigned at gcc dot gnu.org Reporter: kastianoza at gmail dot com Target Milestone: --- It seems that in debug mode gcc generates an 8-bit write opmask, which caus= es half of the result to be skipped when calling '_mm512_fpclass_ps_mask' (whi= ch takes 16 floats and produces 16 bit result). It doesn't happen in O1, when gcc generates instruction that doesn't take writemask. GCC info: Using built-in specs. COLLECT_GCC=3Dg++-11 COLLECT_LTO_WRAPPER=3D/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper OFFLOAD_TARGET_NAMES=3Dnvptx-none:amdgcn-amdhsa OFFLOAD_TARGET_DEFAULT=3D1 Target: x86_64-linux-gnu Configured with: ../src/configure -v --with-pkgversion=3D'Ubuntu 11.1.0-1ubuntu1~18.04.1' --with-bugurl=3Dfile:///usr/share/doc/gcc-11/READM= E.Bugs --enable-languages=3Dc,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --prefix= =3D/usr --with-gcc-major-version-only --program-suffix=3D-11 --program-prefix=3Dx86_64-linux-gnu- --enable-shared --enable-linker-build-= id --libexecdir=3D/usr/lib --without-included-gettext --enable-threads=3Dposix --libdir=3D/usr/lib --enable-nls --enable-clocale=3Dgnu --enable-libstdcxx-= debug --enable-libstdcxx-time=3Dyes --with-default-libstdcxx-abi=3Dnew --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --enable-default-pie --with-system-zlib --enable-libphobos-checking=3Drelea= se --with-target-system-zlib=3Dauto --enable-objc-gc=3Dauto --enable-multiarch --disable-werror --disable-cet --with-arch-32=3Di686 --with-abi=3Dm64 --with-multilib-list=3Dm32,m64,mx32 --enable-multilib --with-tune=3Dgeneric --enable-offload-targets=3Dnvptx-none=3D/build/gcc-11-YRKbe7/gcc-11-11.1.0/= debian/tmp-nvptx/usr,amdgcn-amdhsa=3D/build/gcc-11-YRKbe7/gcc-11-11.1.0/deb= ian/tmp-gcn/usr --without-cuda-driver --enable-checking=3Drelease --build=3Dx86_64-linux-gnu --host=3Dx86_64-linux-gnu --target=3Dx86_64-linux-gnu Thread model: posix Supported LTO compression algorithms: zlib zstd gcc version 11.1.0 (Ubuntu 11.1.0-1ubuntu1~18.04.1)=20 Compilation command: g++-11 fpclass_instruction.cpp -mavx512f -mavx512vl -mavx512bw -mavx512dq -= ggdb -O0 minimal example: #include #include int main() { __m512 x { 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, }; auto ret =3D _mm512_fpclass_ps_mask(x, 0x26); std::cout << ret << std::endl; } relevant part of preprocessed code: (notice incorrect mask type : __mmask8) # 7 "fpclass_instruction.cpp" int main() { __m512 x { 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, }; auto ret =3D=20 # 13 "fpclass_instruction.cpp" 3 4 ((__mmask16) __builtin_ia32_fpclassps512_mask ((__v16sf) (__m51= 2) ( # 13 "fpclass_instruction.cpp" x # 13 "fpclass_instruction.cpp" 3 4 ), (int) ( # 13 "fpclass_instruction.cpp" 0x26 # 13 "fpclass_instruction.cpp" 3 4 ),(__mmask8)-1)) # 13 "fpclass_instruction.cpp" ; std::cout << ret << std::endl; }=