Implementation notes: amd64, cel02, crypto_sign/rainbow1aclassic363232

Computer: cel02
Architecture: amd64
CPU ID: GenuineIntel-00050657-bfebfbff
SUPERCOP version: 20201130
Operation: crypto_sign
Primitive: rainbow1aclassic363232
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
241332109385 8 0166922 896 1656T:avx2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121120201130
298180143617 8 0182347 928 1720T:ssse3gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
32053892419 8 0151003 928 1688T:ssse3gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
34503891274 8 0149059 928 1688T:ssse3gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
37090292379 8 0150642 896 1656T:ssse3clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121120201130
371370103346 0 0173880 896 1656T:amd64clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121120201130
45183486978 0 0157459 920 1688T:amd64gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
48060051742 8 0116811 920 1656T:ssse3gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
59027850901 0 0119914 888 1656T:refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121120201130
606550106784 0 0179979 920 1720T:refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
72295660578 0 0129594 888 1656T:amd64clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121120201130
750024138111 0 0210987 920 1720T:amd64gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
83366288927 0 0159059 920 1688T:amd64gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
105195495283 0 0164832 896 1656T:refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121120201130
125452254878 0 0125395 920 1688T:refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
126902255158 0 0125283 920 1688T:refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
138971029848 0 099491 912 1656T:amd64gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130
198021626857 0 096347 912 1656T:refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121120201130

Compiler output

Implementation: T:amd64
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x558e224511f0: v4i64 = X86ISD::VTRUNC 0x558e224510c0
try.c: 0x558e224510c0: v16i32 = vselect 0x558e22473d00, 0x558e223f9b40, 0x558e22450f90
try.c: 0x558e22473d00: v4i1 = X86ISD::PCMPGTM 0x558e2244a7a0, 0x558e22446330
try.c: 0x558e2244a7a0: v4i64 = X86ISD::VBROADCAST 0x558e22411470
try.c: 0x558e22411470: i64,ch = load<LD8[%lsr.iv6971]> 0x558e2235b940, 0x558e223d6640, undef:i64
try.c: 0x558e223d6640: i64,ch = CopyFromReg 0x558e2235b940, Register:i64 %vreg50
try.c: 0x558e22446590: i64 = Register %vreg50
try.c: 0x558e223f81b0: i64 = undef
try.c: 0x558e22446330: v4i64,ch = CopyFromReg 0x558e2235b940, Register:v4i64 %vreg13
try.c: 0x558e2244aff0: v4i64 = Register %vreg13
try.c: 0x558e223f9b40: v16i32 = X86ISD::VBROADCAST 0x558e2244aa00
try.c: 0x558e2244aa00: i32,ch = load<LD4[ConstantPool]> 0x558e2235b940, 0x558e22410a50, undef:i64
try.c: 0x558e22410a50: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x558e223d9ec0: i64 = TargetConstantPool<i32 1> 0
try.c: 0x558e223f81b0: i64 = undef
try.c: 0x558e22450f90: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x558e22450e60: i32 = Constant<0>
try.c: 0x558e22450e60: i32 = Constant<0>
try.c: 0x558e22450e60: i32 = Constant<0>
try.c: 0x558e22450e60: i32 = Constant<0>
try.c: 0x558e22450e60: i32 = Constant<0>
try.c: 0x558e22450e60: i32 = Constant<0>
try.c: 0x558e22450e60: i32 = Constant<0>
try.c: 0x558e22450e60: i32 = Constant<0>
try.c: 0x558e22450e60: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:amd64

Compiler output

Implementation: T:amd64
Security model: timingleaks
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x55690b2e4e50: v4i64 = X86ISD::VTRUNC 0x55690b2e4d20
try.c: 0x55690b2e4d20: v16i32 = vselect 0x55690b2cec90, 0x55690b266330, 0x55690b2e4bf0
try.c: 0x55690b2cec90: v4i1 = X86ISD::PCMPGTM 0x55690b2cbc60, 0x55690b2c77f0
try.c: 0x55690b2cbc60: v4i64 = X86ISD::VBROADCAST 0x55690b2667f0
try.c: 0x55690b2667f0: i64,ch = load<LD8[%lsr.iv6971]> 0x55690b1c5a40, 0x55690b26c210, undef:i64
try.c: 0x55690b26c210: i64,ch = CopyFromReg 0x55690b1c5a40, Register:i64 %vreg50
try.c: 0x55690b2c7a50: i64 = Register %vreg50
try.c: 0x55690b26eab0: i64 = undef
try.c: 0x55690b2c77f0: v4i64,ch = CopyFromReg 0x55690b1c5a40, Register:v4i64 %vreg13
try.c: 0x55690b2cc4b0: v4i64 = Register %vreg13
try.c: 0x55690b266330: v16i32 = X86ISD::VBROADCAST 0x55690b2cbec0
try.c: 0x55690b2cbec0: i32,ch = load<LD4[ConstantPool]> 0x55690b1c5a40, 0x55690b268cd0, undef:i64
try.c: 0x55690b268cd0: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x55690b26f430: i64 = TargetConstantPool<i32 1> 0
try.c: 0x55690b26eab0: i64 = undef
try.c: 0x55690b2e4bf0: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x55690b2e4ac0: i32 = Constant<0>
try.c: 0x55690b2e4ac0: i32 = Constant<0>
try.c: 0x55690b2e4ac0: i32 = Constant<0>
try.c: 0x55690b2e4ac0: i32 = Constant<0>
try.c: 0x55690b2e4ac0: i32 = Constant<0>
try.c: 0x55690b2e4ac0: i32 = Constant<0>
try.c: 0x55690b2e4ac0: i32 = Constant<0>
try.c: 0x55690b2e4ac0: i32 = Constant<0>
try.c: 0x55690b2e4ac0: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:amd64

Compiler output

Implementation: T:amd64
Security model: timingleaks
Compiler: clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x5620ef452200: v4i64 = X86ISD::VTRUNC 0x5620ef4520d0
try.c: 0x5620ef4520d0: v16i32 = vselect 0x5620ef43dc60, 0x5620ef3e0800, 0x5620ef451fa0
try.c: 0x5620ef43dc60: v4i1 = X86ISD::PCMPGTM 0x5620ef437880, 0x5620ef433410
try.c: 0x5620ef437880: v4i64 = X86ISD::VBROADCAST 0x5620ef3dd9a0
try.c: 0x5620ef3dd9a0: i64,ch = load<LD8[%lsr.iv6971]> 0x5620ef348950, 0x5620ef42aca0, undef:i64
try.c: 0x5620ef42aca0: i64,ch = CopyFromReg 0x5620ef348950, Register:i64 %vreg50
try.c: 0x5620ef433670: i64 = Register %vreg50
try.c: 0x5620ef3dee70: i64 = undef
try.c: 0x5620ef433410: v4i64,ch = CopyFromReg 0x5620ef348950, Register:v4i64 %vreg13
try.c: 0x5620ef4380d0: v4i64 = Register %vreg13
try.c: 0x5620ef3e0800: v16i32 = X86ISD::VBROADCAST 0x5620ef437ae0
try.c: 0x5620ef437ae0: i32,ch = load<LD4[ConstantPool]> 0x5620ef348950, 0x5620ef3d80e0, undef:i64
try.c: 0x5620ef3d80e0: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x5620ef3f1d50: i64 = TargetConstantPool<i32 1> 0
try.c: 0x5620ef3dee70: i64 = undef
try.c: 0x5620ef451fa0: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x5620ef451e70: i32 = Constant<0>
try.c: 0x5620ef451e70: i32 = Constant<0>
try.c: 0x5620ef451e70: i32 = Constant<0>
try.c: 0x5620ef451e70: i32 = Constant<0>
try.c: 0x5620ef451e70: i32 = Constant<0>
try.c: 0x5620ef451e70: i32 = Constant<0>
try.c: 0x5620ef451e70: i32 = Constant<0>
try.c: 0x5620ef451e70: i32 = Constant<0>
try.c: 0x5620ef451e70: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:amd64

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x555f205024f0: v4i64 = X86ISD::VTRUNC 0x555f205023c0
try.c: 0x555f205023c0: v16i32 = vselect 0x555f204ee7d0, 0x555f2048c310, 0x555f20502290
try.c: 0x555f204ee7d0: v4i1 = X86ISD::PCMPGTM 0x555f204e7b70, 0x555f204e3700
try.c: 0x555f204e7b70: v4i64 = X86ISD::VBROADCAST 0x555f20491b30
try.c: 0x555f20491b30: i64,ch = load<LD8[%lsr.iv6971]> 0x555f203f8950, 0x555f204de560, undef:i64
try.c: 0x555f204de560: i64,ch = CopyFromReg 0x555f203f8950, Register:i64 %vreg50
try.c: 0x555f204e3960: i64 = Register %vreg50
try.c: 0x555f2048a980: i64 = undef
try.c: 0x555f204e3700: v4i64,ch = CopyFromReg 0x555f203f8950, Register:v4i64 %vreg13
try.c: 0x555f204e83c0: v4i64 = Register %vreg13
try.c: 0x555f2048c310: v16i32 = X86ISD::VBROADCAST 0x555f204e7dd0
try.c: 0x555f204e7dd0: i32,ch = load<LD4[ConstantPool]> 0x555f203f8950, 0x555f20491110, undef:i64
try.c: 0x555f20491110: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x555f204cd070: i64 = TargetConstantPool<i32 1> 0
try.c: 0x555f2048a980: i64 = undef
try.c: 0x555f20502290: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x555f20502160: i32 = Constant<0>
try.c: 0x555f20502160: i32 = Constant<0>
try.c: 0x555f20502160: i32 = Constant<0>
try.c: 0x555f20502160: i32 = Constant<0>
try.c: 0x555f20502160: i32 = Constant<0>
try.c: 0x555f20502160: i32 = Constant<0>
try.c: 0x555f20502160: i32 = Constant<0>
try.c: 0x555f20502160: i32 = Constant<0>
try.c: 0x555f20502160: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:avx2

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x5617f5b0adf0: v4i64 = X86ISD::VTRUNC 0x5617f5b0acc0
try.c: 0x5617f5b0acc0: v16i32 = vselect 0x5617f5b0ecb0, 0x5617f5aa0b20, 0x5617f5b0ab90
try.c: 0x5617f5b0ecb0: v4i1 = X86ISD::PCMPGTM 0x5617f5af31f0, 0x5617f5aeed80
try.c: 0x5617f5af31f0: v4i64 = X86ISD::VBROADCAST 0x5617f5aa0fe0
try.c: 0x5617f5aa0fe0: i64,ch = load<LD8[%lsr.iv6971]> 0x5617f59eda20, 0x5617f5a90530, undef:i64
try.c: 0x5617f5a90530: i64,ch = CopyFromReg 0x5617f59eda20, Register:i64 %vreg50
try.c: 0x5617f5aeefe0: i64 = Register %vreg50
try.c: 0x5617f5a9d8f0: i64 = undef
try.c: 0x5617f5aeed80: v4i64,ch = CopyFromReg 0x5617f59eda20, Register:v4i64 %vreg13
try.c: 0x5617f5af3a40: v4i64 = Register %vreg13
try.c: 0x5617f5aa0b20: v16i32 = X86ISD::VBROADCAST 0x5617f5af3450
try.c: 0x5617f5af3450: i32,ch = load<LD4[ConstantPool]> 0x5617f59eda20, 0x5617f5a8eb00, undef:i64
try.c: 0x5617f5a8eb00: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x5617f5a9e270: i64 = TargetConstantPool<i32 1> 0
try.c: 0x5617f5a9d8f0: i64 = undef
try.c: 0x5617f5b0ab90: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x5617f5b0aa60: i32 = Constant<0>
try.c: 0x5617f5b0aa60: i32 = Constant<0>
try.c: 0x5617f5b0aa60: i32 = Constant<0>
try.c: 0x5617f5b0aa60: i32 = Constant<0>
try.c: 0x5617f5b0aa60: i32 = Constant<0>
try.c: 0x5617f5b0aa60: i32 = Constant<0>
try.c: 0x5617f5b0aa60: i32 = Constant<0>
try.c: 0x5617f5b0aa60: i32 = Constant<0>
try.c: 0x5617f5b0aa60: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:avx2

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x55f2cf1d63e0: v4i64 = X86ISD::VTRUNC 0x55f2cf1d62b0
try.c: 0x55f2cf1d62b0: v16i32 = vselect 0x55f2cf1d0db0, 0x55f2cf160fe0, 0x55f2cf1d6180
try.c: 0x55f2cf1d0db0: v4i1 = X86ISD::PCMPGTM 0x55f2cf1b9a40, 0x55f2cf1b55d0
try.c: 0x55f2cf1b9a40: v4i64 = X86ISD::VBROADCAST 0x55f2cf159400
try.c: 0x55f2cf159400: i64,ch = load<LD8[%lsr.iv6971]> 0x55f2cf0ca930, 0x55f2cf19aae0, undef:i64
try.c: 0x55f2cf19aae0: i64,ch = CopyFromReg 0x55f2cf0ca930, Register:i64 %vreg50
try.c: 0x55f2cf1b5830: i64 = Register %vreg50
try.c: 0x55f2cf15a8d0: i64 = undef
try.c: 0x55f2cf1b55d0: v4i64,ch = CopyFromReg 0x55f2cf0ca930, Register:v4i64 %vreg13
try.c: 0x55f2cf1ba290: v4i64 = Register %vreg13
try.c: 0x55f2cf160fe0: v16i32 = X86ISD::VBROADCAST 0x55f2cf1b9ca0
try.c: 0x55f2cf1b9ca0: i32,ch = load<LD4[ConstantPool]> 0x55f2cf0ca930, 0x55f2cf1589e0, undef:i64
try.c: 0x55f2cf1589e0: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x55f2cf1a4b40: i64 = TargetConstantPool<i32 1> 0
try.c: 0x55f2cf15a8d0: i64 = undef
try.c: 0x55f2cf1d6180: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x55f2cf1d6050: i32 = Constant<0>
try.c: 0x55f2cf1d6050: i32 = Constant<0>
try.c: 0x55f2cf1d6050: i32 = Constant<0>
try.c: 0x55f2cf1d6050: i32 = Constant<0>
try.c: 0x55f2cf1d6050: i32 = Constant<0>
try.c: 0x55f2cf1d6050: i32 = Constant<0>
try.c: 0x55f2cf1d6050: i32 = Constant<0>
try.c: 0x55f2cf1d6050: i32 = Constant<0>
try.c: 0x55f2cf1d6050: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:avx2

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
blas_comm.c: In file included from blas_comm.c:6:
blas_comm.c: In file included from ./blas.h:25:
blas_comm.c: ./blas_avx2.h:88:17: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'gf256v_add_avx2' that is compiled without support for 'sse4.2'
blas_comm.c: __m256i inp = _mm256_loadu_si256( (__m256i*) (a+i*32) );
blas_comm.c: ^
blas_comm.c: ./blas_avx2.h:89:17: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'gf256v_add_avx2' that is compiled without support for 'sse4.2'
blas_comm.c: __m256i out = _mm256_loadu_si256( (__m256i*) (accu_b+i*32) );
blas_comm.c: ^
blas_comm.c: ./blas_avx2.h:91:3: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'gf256v_add_avx2' that is compiled without support for 'sse4.2'
blas_comm.c: _mm256_storeu_si256( (__m256i*) (accu_b+i*32) , out );
blas_comm.c: ^
blas_comm.c: fatal error: error in backend: Do not know how to split this operator's operand!
blas_comm.c:
blas_comm.c: clang: error: clang frontend command failed with exit code 70 (use -v to see invocation)
blas_comm.c: clang version 3.8.1-24 (tags/RELEASE_381/final)
blas_comm.c: Target: x86_64-pc-linux-gnu
blas_comm.c: Thread model: posix
blas_comm.c: InstalledDir: /usr/bin
blas_comm.c: clang: note: diagnostic msg: PLEASE submit a bug report to http://llvm.org/bugs/ and include the crash backtrace, preprocessed source, and associated run script.
blas_comm.c: clang: note: diagnostic msg:
blas_comm.c: ********************
blas_comm.c:
blas_comm.c: PLEASE ATTACH THE FOLLOWING FILES TO THE BUG REPORT:
blas_comm.c: Preprocessed source(s) and associated run script(s) are located at:
blas_comm.c: clang: note: diagnostic msg: /tmp/blas_comm-ba6965.c
blas_comm.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:avx2

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
blas_matrix_avx2.c: blas_matrix_avx2.c: In function '_gf256mat_gauss_elim_avx2_32x':
blas_matrix_avx2.c: blas_matrix_avx2.c:479:19: warning: implicit declaration of function '_mm256_setr_m128i' [-Wimplicit-function-declaration]
blas_matrix_avx2.c: __m256i mask = _mm256_setr_m128i( add_mask , add_mask );
blas_matrix_avx2.c: ^~~~~~~~~~~~~~~~~
blas_matrix_avx2.c: blas_matrix_avx2.c:479:19: error: incompatible types when initializing type '__m256i {aka __vector(4) long long int}' using type 'int'
blas_matrix_avx2.c: blas_matrix_avx2.c:495:17: error: incompatible types when initializing type '__m256i {aka __vector(4) long long int}' using type 'int'
blas_matrix_avx2.c: __m256i pi2 = _mm256_setr_m128i( pi1 , pi1 );
blas_matrix_avx2.c: ^~~~~~~~~~~~~~~~~
Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE T:avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE T:avx2

Compiler output

Implementation: T:ref
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x55da3ee518a0: v4i64 = X86ISD::VTRUNC 0x55da3ee51770
try.c: 0x55da3ee51770: v16i32 = vselect 0x55da3ee3f000, 0x55da3edda2a0, 0x55da3ee51640
try.c: 0x55da3ee3f000: v4i1 = X86ISD::PCMPGTM 0x55da3ee33700, 0x55da3ee2f290
try.c: 0x55da3ee33700: v4i64 = X86ISD::VBROADCAST 0x55da3edd62c0
try.c: 0x55da3edd62c0: i64,ch = load<LD8[%lsr.iv6971]> 0x55da3ed44940, 0x55da3ee261c0, undef:i64
try.c: 0x55da3ee261c0: i64,ch = CopyFromReg 0x55da3ed44940, Register:i64 %vreg50
try.c: 0x55da3ee2f4f0: i64 = Register %vreg50
try.c: 0x55da3edd7790: i64 = undef
try.c: 0x55da3ee2f290: v4i64,ch = CopyFromReg 0x55da3ed44940, Register:v4i64 %vreg13
try.c: 0x55da3ee33f50: v4i64 = Register %vreg13
try.c: 0x55da3edda2a0: v16i32 = X86ISD::VBROADCAST 0x55da3ee33960
try.c: 0x55da3ee33960: i32,ch = load<LD4[ConstantPool]> 0x55da3ed44940, 0x55da3edfa8c0, undef:i64
try.c: 0x55da3edfa8c0: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x55da3ee1cc90: i64 = TargetConstantPool<i32 1> 0
try.c: 0x55da3edd7790: i64 = undef
try.c: 0x55da3ee51640: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x55da3ee51510: i32 = Constant<0>
try.c: 0x55da3ee51510: i32 = Constant<0>
try.c: 0x55da3ee51510: i32 = Constant<0>
try.c: 0x55da3ee51510: i32 = Constant<0>
try.c: 0x55da3ee51510: i32 = Constant<0>
try.c: 0x55da3ee51510: i32 = Constant<0>
try.c: 0x55da3ee51510: i32 = Constant<0>
try.c: 0x55da3ee51510: i32 = Constant<0>
try.c: 0x55da3ee51510: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:ref

Compiler output

Implementation: T:ref
Security model: timingleaks
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x557df4dc3a30: v4i64 = X86ISD::VTRUNC 0x557df4dc3900
try.c: 0x557df4dc3900: v16i32 = vselect 0x557df4da07d0, 0x557df4d461e0, 0x557df4dc37d0
try.c: 0x557df4da07d0: v4i1 = X86ISD::PCMPGTM 0x557df4daa240, 0x557df4da6c20
try.c: 0x557df4daa240: v4i64 = X86ISD::VBROADCAST 0x557df4d466a0
try.c: 0x557df4d466a0: i64,ch = load<LD8[%lsr.iv6971]> 0x557df4ca4a30, 0x557df4d4c180, undef:i64
try.c: 0x557df4d4c180: i64,ch = CopyFromReg 0x557df4ca4a30, Register:i64 %vreg50
try.c: 0x557df4da6e80: i64 = Register %vreg50
try.c: 0x557df4d2b9c0: i64 = undef
try.c: 0x557df4da6c20: v4i64,ch = CopyFromReg 0x557df4ca4a30, Register:v4i64 %vreg13
try.c: 0x557df4daaa90: v4i64 = Register %vreg13
try.c: 0x557df4d461e0: v16i32 = X86ISD::VBROADCAST 0x557df4daa4a0
try.c: 0x557df4daa4a0: i32,ch = load<LD4[ConstantPool]> 0x557df4ca4a30, 0x557df4d4a750, undef:i64
try.c: 0x557df4d4a750: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x557df4d2c340: i64 = TargetConstantPool<i32 1> 0
try.c: 0x557df4d2b9c0: i64 = undef
try.c: 0x557df4dc37d0: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x557df4dc36a0: i32 = Constant<0>
try.c: 0x557df4dc36a0: i32 = Constant<0>
try.c: 0x557df4dc36a0: i32 = Constant<0>
try.c: 0x557df4dc36a0: i32 = Constant<0>
try.c: 0x557df4dc36a0: i32 = Constant<0>
try.c: 0x557df4dc36a0: i32 = Constant<0>
try.c: 0x557df4dc36a0: i32 = Constant<0>
try.c: 0x557df4dc36a0: i32 = Constant<0>
try.c: 0x557df4dc36a0: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:ref

Compiler output

Implementation: T:ref
Security model: timingleaks
Compiler: clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x563bfd6d2c70: v4i64 = X86ISD::VTRUNC 0x563bfd6d2b40
try.c: 0x563bfd6d2b40: v16i32 = vselect 0x563bfd6ebfe0, 0x563bfd66eda0, 0x563bfd6d2a10
try.c: 0x563bfd6ebfe0: v4i1 = X86ISD::PCMPGTM 0x563bfd6cd640, 0x563bfd6cb160
try.c: 0x563bfd6cd640: v4i64 = X86ISD::VBROADCAST 0x563bfd672bc0
try.c: 0x563bfd672bc0: i64,ch = load<LD8[%lsr.iv6971]> 0x563bfd5df9d0, 0x563bfd68c720, undef:i64
try.c: 0x563bfd68c720: i64,ch = CopyFromReg 0x563bfd5df9d0, Register:i64 %vreg50
try.c: 0x563bfd6cb3c0: i64 = Register %vreg50
try.c: 0x563bfd66d410: i64 = undef
try.c: 0x563bfd6cb160: v4i64,ch = CopyFromReg 0x563bfd5df9d0, Register:v4i64 %vreg13
try.c: 0x563bfd6cde90: v4i64 = Register %vreg13
try.c: 0x563bfd66eda0: v16i32 = X86ISD::VBROADCAST 0x563bfd6cd8a0
try.c: 0x563bfd6cd8a0: i32,ch = load<LD4[ConstantPool]> 0x563bfd5df9d0, 0x563bfd6721a0, undef:i64
try.c: 0x563bfd6721a0: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x563bfd6b45f0: i64 = TargetConstantPool<i32 1> 0
try.c: 0x563bfd66d410: i64 = undef
try.c: 0x563bfd6d2a10: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x563bfd6d28e0: i32 = Constant<0>
try.c: 0x563bfd6d28e0: i32 = Constant<0>
try.c: 0x563bfd6d28e0: i32 = Constant<0>
try.c: 0x563bfd6d28e0: i32 = Constant<0>
try.c: 0x563bfd6d28e0: i32 = Constant<0>
try.c: 0x563bfd6d28e0: i32 = Constant<0>
try.c: 0x563bfd6d28e0: i32 = Constant<0>
try.c: 0x563bfd6d28e0: i32 = Constant<0>
try.c: 0x563bfd6d28e0: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:ref

Compiler output

Implementation: T:ssse3
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x55ff2ba91da0: v4i64 = X86ISD::VTRUNC 0x55ff2ba91c70
try.c: 0x55ff2ba91c70: v16i32 = vselect 0x55ff2ba958c0, 0x55ff2ba36a40, 0x55ff2ba91b40
try.c: 0x55ff2ba958c0: v4i1 = X86ISD::PCMPGTM 0x55ff2ba8e790, 0x55ff2ba8a320
try.c: 0x55ff2ba8e790: v4i64 = X86ISD::VBROADCAST 0x55ff2ba173d0
try.c: 0x55ff2ba173d0: i64,ch = load<LD8[%lsr.iv6971]> 0x55ff2b99f960, 0x55ff2ba77fb0, undef:i64
try.c: 0x55ff2ba77fb0: i64,ch = CopyFromReg 0x55ff2b99f960, Register:i64 %vreg50
try.c: 0x55ff2ba8a580: i64 = Register %vreg50
try.c: 0x55ff2ba350b0: i64 = undef
try.c: 0x55ff2ba8a320: v4i64,ch = CopyFromReg 0x55ff2b99f960, Register:v4i64 %vreg13
try.c: 0x55ff2ba8efe0: v4i64 = Register %vreg13
try.c: 0x55ff2ba36a40: v16i32 = X86ISD::VBROADCAST 0x55ff2ba8e9f0
try.c: 0x55ff2ba8e9f0: i32,ch = load<LD4[ConstantPool]> 0x55ff2b99f960, 0x55ff2ba169b0, undef:i64
try.c: 0x55ff2ba169b0: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x55ff2ba791b0: i64 = TargetConstantPool<i32 1> 0
try.c: 0x55ff2ba350b0: i64 = undef
try.c: 0x55ff2ba91b40: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x55ff2ba91a10: i32 = Constant<0>
try.c: 0x55ff2ba91a10: i32 = Constant<0>
try.c: 0x55ff2ba91a10: i32 = Constant<0>
try.c: 0x55ff2ba91a10: i32 = Constant<0>
try.c: 0x55ff2ba91a10: i32 = Constant<0>
try.c: 0x55ff2ba91a10: i32 = Constant<0>
try.c: 0x55ff2ba91a10: i32 = Constant<0>
try.c: 0x55ff2ba91a10: i32 = Constant<0>
try.c: 0x55ff2ba91a10: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:ssse3

Compiler output

Implementation: T:ssse3
Security model: timingleaks
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x5611ce363e80: v4i64 = X86ISD::VTRUNC 0x5611ce363d50
try.c: 0x5611ce363d50: v16i32 = vselect 0x5611ce340eb0, 0x5611ce2dad60, 0x5611ce363c20
try.c: 0x5611ce340eb0: v4i1 = X86ISD::PCMPGTM 0x5611ce33fea0, 0x5611ce33ba30
try.c: 0x5611ce33fea0: v4i64 = X86ISD::VBROADCAST 0x5611ce2db220
try.c: 0x5611ce2db220: i64,ch = load<LD8[%lsr.iv6971]> 0x5611ce239a40, 0x5611ce2d42c0, undef:i64
try.c: 0x5611ce2d42c0: i64,ch = CopyFromReg 0x5611ce239a40, Register:i64 %vreg50
try.c: 0x5611ce33bc90: i64 = Register %vreg50
try.c: 0x5611ce2b7030: i64 = undef
try.c: 0x5611ce33ba30: v4i64,ch = CopyFromReg 0x5611ce239a40, Register:v4i64 %vreg13
try.c: 0x5611ce3406f0: v4i64 = Register %vreg13
try.c: 0x5611ce2dad60: v16i32 = X86ISD::VBROADCAST 0x5611ce340100
try.c: 0x5611ce340100: i32,ch = load<LD4[ConstantPool]> 0x5611ce239a40, 0x5611ce2d8490, undef:i64
try.c: 0x5611ce2d8490: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x5611ce2b79b0: i64 = TargetConstantPool<i32 1> 0
try.c: 0x5611ce2b7030: i64 = undef
try.c: 0x5611ce363c20: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x5611ce363af0: i32 = Constant<0>
try.c: 0x5611ce363af0: i32 = Constant<0>
try.c: 0x5611ce363af0: i32 = Constant<0>
try.c: 0x5611ce363af0: i32 = Constant<0>
try.c: 0x5611ce363af0: i32 = Constant<0>
try.c: 0x5611ce363af0: i32 = Constant<0>
try.c: 0x5611ce363af0: i32 = Constant<0>
try.c: 0x5611ce363af0: i32 = Constant<0>
try.c: 0x5611ce363af0: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:ssse3

Compiler output

Implementation: T:ssse3
Security model: timingleaks
Compiler: clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
try.c: fatal error: error in backend: Cannot select: 0x561a603637e0: v4i64 = X86ISD::VTRUNC 0x561a603636b0
try.c: 0x561a603636b0: v16i32 = vselect 0x561a6034eea0, 0x561a60306f20, 0x561a60363580
try.c: 0x561a6034eea0: v4i1 = X86ISD::PCMPGTM 0x561a6034be80, 0x561a60347a10
try.c: 0x561a6034be80: v4i64 = X86ISD::VBROADCAST 0x561a602ecae0
try.c: 0x561a602ecae0: i64,ch = load<LD8[%lsr.iv6971]> 0x561a6025c950, 0x561a6033f100, undef:i64
try.c: 0x561a6033f100: i64,ch = CopyFromReg 0x561a6025c950, Register:i64 %vreg50
try.c: 0x561a60347c70: i64 = Register %vreg50
try.c: 0x561a60305590: i64 = undef
try.c: 0x561a60347a10: v4i64,ch = CopyFromReg 0x561a6025c950, Register:v4i64 %vreg13
try.c: 0x561a6034c6d0: v4i64 = Register %vreg13
try.c: 0x561a60306f20: v16i32 = X86ISD::VBROADCAST 0x561a6034c0e0
try.c: 0x561a6034c0e0: i32,ch = load<LD4[ConstantPool]> 0x561a6025c950, 0x561a602ec0c0, undef:i64
try.c: 0x561a602ec0c0: i64 = X86ISD::WrapperRIP TargetConstantPool:i64<i32 1> 0
try.c: 0x561a60304010: i64 = TargetConstantPool<i32 1> 0
try.c: 0x561a60305590: i64 = undef
try.c: 0x561a60363580: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x561a60363450: i32 = Constant<0>
try.c: 0x561a60363450: i32 = Constant<0>
try.c: 0x561a60363450: i32 = Constant<0>
try.c: 0x561a60363450: i32 = Constant<0>
try.c: 0x561a60363450: i32 = Constant<0>
try.c: 0x561a60363450: i32 = Constant<0>
try.c: 0x561a60363450: i32 = Constant<0>
try.c: 0x561a60363450: i32 = Constant<0>
try.c: 0x561a60363450: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:ssse3

Compiler output

Implementation: T:ssse3
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
blas_matrix_ref.c: In file included from blas_matrix_ref.c:6:
blas_matrix_ref.c: In file included from ./blas.h:25:
blas_matrix_ref.c: In file included from ./blas_sse.h:16:
blas_matrix_ref.c: ./gf16_sse.h:34:9: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'linear_transform_8x8_128b' that is compiled without support for 'ssse3'
blas_matrix_ref.c: return _mm_shuffle_epi8(tab_l,v&mask_f)^_mm_shuffle_epi8(tab_h,_mm_srli_epi16(v,4)&mask_f);
blas_matrix_ref.c: ^
blas_matrix_ref.c: ./gf16_sse.h:34:42: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'linear_transform_8x8_128b' that is compiled without support for 'ssse3'
blas_matrix_ref.c: return _mm_shuffle_epi8(tab_l,v&mask_f)^_mm_shuffle_epi8(tab_h,_mm_srli_epi16(v,4)&mask_f);
blas_matrix_ref.c: ^
blas_matrix_ref.c: fatal error: error in backend: Cannot select: 0x55cda3dc1c00: v16i8 = X86ISD::PSHUFB 0x55cda3cff650, 0x55cda3da3240
blas_matrix_ref.c: 0x55cda3cff650: v16i8,ch = CopyFromReg 0x55cda3c7b5b0, Register:v16i8 %vreg15
blas_matrix_ref.c: 0x55cda3da2660: v16i8 = Register %vreg15
blas_matrix_ref.c: 0x55cda3da3240: v16i8 = bitcast 0x55cda3d5e930
blas_matrix_ref.c: 0x55cda3d5e930: v2i64 = and 0x55cda3d74b50, 0x55cda3d5f2b0
blas_matrix_ref.c: 0x55cda3d74b50: v2i64 = bitcast 0x55cda3d741d0
blas_matrix_ref.c: 0x55cda3d741d0: v8i16 = X86ISD::VSRLI 0x55cda3cffb10, Constant:i8<4>
blas_matrix_ref.c: 0x55cda3cffb10: v8i16 = bitcast 0x55cda3d74690
blas_matrix_ref.c: 0x55cda3d74690: v2i64,ch = load<LD16[%uglygep1617](align=1)(tbaa=<0x55cda3900628>)> 0x55cda3c7b5b0, 0x55cda3d5e470, undef:i64
blas_matrix_ref.c: 0x55cda3d5e470: i64 = add 0x55cda3d74300, 0x55cda3d74db0
blas_matrix_ref.c: 0x55cda3d74300: i64,ch = CopyFromReg 0x55cda3c7b5b0, Register:i64 %vreg12
blas_matrix_ref.c: 0x55cda3d75010: i64 = Register %vreg12
blas_matrix_ref.c: 0x55cda3d74db0: i64,ch = CopyFromReg 0x55cda3c7b5b0, Register:i64 %vreg17
blas_matrix_ref.c: 0x55cda3d748f0: i64 = Register %vreg17
blas_matrix_ref.c: 0x55cda3cffc40: i64 = undef
blas_matrix_ref.c: 0x55cda3da3110: i8 = Constant<4>
blas_matrix_ref.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:ssse3