Implementation notes: amd64, oki, crypto_core/salsa20

Computer: oki
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20181123
Operation: crypto_core
Primitive: salsa20

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
444	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20181127	20181123
444	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20181127	20181123
446	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20181127	20181123
446	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20181127	20181123
446	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20181127	20181123
446	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20181127	20181123
446	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-O3_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20181127	20181123
448	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20181127	20181123
450	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20181127	20181123
450	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20181127	20181123
450	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20181127	20181123
450	? ? ?	? ? ?	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20181127	20181123
450	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20181127	20181123
450	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20181127	20181123
450	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20181127	20181123
452	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20181127	20181123
454	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20181127	20181123
454	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20181127	20181123
456	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20181127	20181123
456	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20181127	20181123
456	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20181127	20181123
456	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20181127	20181123
458	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20181127	20181123
458	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20181127	20181123
464	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20181127	20181123
476	? ? ?	? ? ?	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20181127	20181123
482	? ? ?	? ? ?	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20181127	20181123
482	? ? ?	? ? ?	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20181127	20181123
482	? ? ?	? ? ?	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20181127	20181123
548	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20181127	20181123
556	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20181127	20181123
556	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20181127	20181123
558	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20181127	20181123
558	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20181127	20181123
558	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20181127	20181123
558	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20181127	20181123
560	? ? ?	? ? ?	`ref`	`gcc_-Os_-fomit-frame-pointer`	20181127	20181123
562	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20181127	20181123
562	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20181127	20181123
562	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20181127	20181123
562	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20181127	20181123
564	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20181127	20181123
564	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20181127	20181123
564	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20181127	20181123
564	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20181127	20181123
566	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer`	20181127	20181123
566	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20181127	20181123
566	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20181127	20181123
566	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20181127	20181123
568	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20181127	20181123
568	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20181127	20181123
568	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20181127	20181123
568	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20181127	20181123
568	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20181127	20181123
568	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20181127	20181123
568	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20181127	20181123
568	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20181127	20181123
570	? ? ?	? ? ?	`ref`	`gcc_-O_-fomit-frame-pointer`	20181127	20181123
570	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20181127	20181123
570	? ? ?	? ? ?	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20181127	20181123
570	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20181127	20181123
570	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20181127	20181123
570	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20181127	20181123
570	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20181127	20181123
572	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20181127	20181123
572	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20181127	20181123
572	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20181127	20181123
574	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20181127	20181123
574	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer`	20181127	20181123
574	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20181127	20181123
576	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20181127	20181123
576	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20181127	20181123
580	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20181127	20181123
580	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20181127	20181123
582	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20181127	20181123
582	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20181127	20181123
582	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20181127	20181123
584	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20181127	20181123
584	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20181127	20181123
584	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20181127	20181123
586	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20181127	20181123
590	? ? ?	? ? ?	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20181127	20181123
592	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20181127	20181123
834	? ? ?	? ? ?	`ref`	`clang_-O3_-fwrapv_-march=x86-64_-mcpu=core-avx2_-mavx2_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20181127	20181123
834	? ? ?	? ? ?	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20181127	20181123
834	? ? ?	? ? ?	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20181127	20181123
836	? ? ?	? ? ?	`ref`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20181127	20181123
2808	? ? ?	? ? ?	`ref`	`cc`	20181127	20181123
2868	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops`	20181127	20181123
2888	? ? ?	? ? ?	`ref`	`gcc`	20181127	20181123

Compiler output

Implementation: ref
Security model: unknown
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

try.c: fatal error: error in backend: Cannot select: 0x1471c00: v4i64 = X86ISD::VTRUNC 0x1471a30
try.c: 0x1471a30: v16i32 = vselect 0x1479940, 0x140bd20, 0x1471900
try.c: 0x1479940: v4i1 = X86ISD::PCMPGTM 0x145bd00, 0x140cad0
try.c: 0x145bd00: v4i64 = X86ISD::VBROADCAST 0x140ce60
try.c: 0x140ce60: i64,ch = load<LD8[%uglygep72]> 0x1356de0, 0x1441e90, undef:i64
try.c: 0x1441e90: i64 = add 0x145cbe0, 0x13f5910
try.c: 0x145cbe0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x14460d0: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x13f5910: i64 = shl 0x1445880, Constant:i8<3>
try.c: 0x1445880: i64,ch = CopyFromReg 0x1356de0, Register:i64 %vreg50
try.c: 0x145d0a0: i64 = Register %vreg50
try.c: 0x13f6f10: i8 = Constant<3>
try.c: 0x145a370: i64 = undef
try.c: 0x140cad0: v4i64,ch = CopyFromReg 0x1356de0, Register:v4i64 %vreg13
try.c: 0x141f230: v4i64 = Register %vreg13
try.c: 0x140bd20: v16i32 = X86ISD::VBROADCAST 0x1445ae0
try.c: 0x1445ae0: i32,ch = load<LD4[ConstantPool]> 0x1356de0, 0x1471570, undef:i64
try.c: 0x1471570: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x141c540: i64 = TargetConstantPool<i32 1> 0
try.c: 0x145a370: i64 = undef
try.c: 0x1471900: 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: 0x14717d0: i32 = Constant<0>
try.c: 0x14717d0: i32 = Constant<0>
try.c: 0x14717d0: i32 = Constant<0>
try.c: 0x14717d0: i32 = Constant<0>
try.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	ref

Compiler output

Implementation: ref
Security model: unknown
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

try.c: fatal error: error in backend: Cannot select: 0xe0b130: v4i64 = X86ISD::VTRUNC 0xe0af60
try.c: 0xe0af60: v16i32 = vselect 0xdfaa40, 0xd8c800, 0xe0ae30
try.c: 0xdfaa40: v4i1 = X86ISD::PCMPGTM 0xdf2a10, 0xd8d5b0
try.c: 0xdf2a10: v4i64 = X86ISD::VBROADCAST 0xd8d940
try.c: 0xd8d940: i64,ch = load<LD8[%uglygep72]> 0xcecda0, 0xdad5b0, undef:i64
try.c: 0xdad5b0: i64 = add 0xdf38f0, 0xd82160
try.c: 0xdf38f0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0xde3c30: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0xd82160: i64 = shl 0xde33e0, Constant:i8<3>
try.c: 0xde33e0: i64,ch = CopyFromReg 0xcecda0, Register:i64 %vreg50
try.c: 0xdf3db0: i64 = Register %vreg50
try.c: 0xd9fc20: i8 = Constant<3>
try.c: 0xdf1080: i64 = undef
try.c: 0xd8d5b0: v4i64,ch = CopyFromReg 0xcecda0, Register:v4i64 %vreg13
try.c: 0xdb1ba0: v4i64 = Register %vreg13
try.c: 0xd8c800: v16i32 = X86ISD::VBROADCAST 0xde3640
try.c: 0xde3640: i32,ch = load<LD4[ConstantPool]> 0xcecda0, 0xe0aaa0, undef:i64
try.c: 0xe0aaa0: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0xd87ef0: i64 = TargetConstantPool<i32 1> 0
try.c: 0xdf1080: i64 = undef
try.c: 0xe0ae30: 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: 0xe0ad00: i32 = Constant<0>
try.c: 0xe0ad00: i32 = Constant<0>
try.c: 0xe0ad00: i32 = Constant<0>
try.c: 0xe0ad00: i32 = Constant<0>
try.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref