Implementation notes: amd64, cryptologic, crypto_hash/blake2s

Computer: cryptologic
Architecture: amd64
CPU ID: GenuineIntel-000206c2-bfebfbff
SUPERCOP version: 20140517
Operation: crypto_hash
Primitive: blake2s
TimeImplementationCompilerBenchmark dateSUPERCOP version
19283xmmgcc -m64 -march=core2 -O -fomit-frame-pointer2014051920140517
19550xmmgcc -m64 -march=core2 -O3 -fomit-frame-pointer2014051920140517
19558xmmgcc -m64 -march=core2 -O2 -fomit-frame-pointer2014051920140517
21300xmmgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2014051920140517
22558xmmgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2014051920140517
22558xmmgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2014051920140517
22658xmmgcc -funroll-loops -O -fomit-frame-pointer2014051920140517
22683xmmgcc -march=nocona -O2 -fomit-frame-pointer2014051920140517
22684xmmgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2014051920140517
22684xmmgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2014051920140517
22691xmmgcc -m64 -march=nocona -O2 -fomit-frame-pointer2014051920140517
22700xmmgcc -funroll-loops -m64 -O -fomit-frame-pointer2014051920140517
22716xmmgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2014051920140517
22775xmmgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2014051920140517
22792xmmgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2014051920140517
22792xmmgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2014051920140517
22792xmmgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2014051920140517
22808xmmgcc -m64 -march=nocona -O3 -fomit-frame-pointer2014051920140517
22809xmmgcc -march=k8 -O -fomit-frame-pointer2014051920140517
22825xmmgcc -m64 -march=k8 -O -fomit-frame-pointer2014051920140517
22825xmmgcc -march=nocona -O3 -fomit-frame-pointer2014051920140517
22850xmmgcc -O -fomit-frame-pointer2014051920140517
22850xmmgcc -m64 -O -fomit-frame-pointer2014051920140517
22866xmmgcc -march=nocona -O -fomit-frame-pointer2014051920140517
22883xmmgcc -m64 -march=nocona -O -fomit-frame-pointer2014051920140517
22884xmmgcc -fno-schedule-insns -O -fomit-frame-pointer2014051920140517
23066xmmgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2014051920140517
23075xmmgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2014051920140517
23084xmmgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2014051920140517
23192xmmgcc -m64 -O2 -fomit-frame-pointer2014051920140517
23200xmmgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2014051920140517
23200xmmgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2014051920140517
23208xmmgcc -O3 -fomit-frame-pointer2014051920140517
23208xmmgcc -fno-schedule-insns -O3 -fomit-frame-pointer2014051920140517
23208xmmgcc -funroll-loops -O3 -fomit-frame-pointer2014051920140517
23208xmmgcc -m64 -O3 -fomit-frame-pointer2014051920140517
23217xmmgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2014051920140517
23233xmmgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2014051920140517
23241xmmgcc -funroll-loops -O2 -fomit-frame-pointer2014051920140517
23242xmmgcc -fno-schedule-insns -O2 -fomit-frame-pointer2014051920140517
23266xmmgcc -O2 -fomit-frame-pointer2014051920140517
23275xmmgcc -march=k8 -O2 -fomit-frame-pointer2014051920140517
23283xmmgcc -m64 -march=k8 -O3 -fomit-frame-pointer2014051920140517
23308xmmgcc -march=k8 -O3 -fomit-frame-pointer2014051920140517
23309xmmgcc -m64 -march=k8 -O2 -fomit-frame-pointer2014051920140517
30750xmmgcc -m64 -march=core2 -Os -fomit-frame-pointer2014051920140517
32967regsgcc -funroll-loops -Os -fomit-frame-pointer2014051920140517
32967regsgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2014051920140517
32967regsgcc -funroll-loops -m64 -Os -fomit-frame-pointer2014051920140517
33050regsgcc -m64 -Os -fomit-frame-pointer2014051920140517
33116regsgcc -fno-schedule-insns -Os -fomit-frame-pointer2014051920140517
33141regsgcc -Os -fomit-frame-pointer2014051920140517
33308regsgcc -m64 -march=core2 -Os -fomit-frame-pointer2014051920140517
33367regsgcc -m64 -march=k8 -Os -fomit-frame-pointer2014051920140517
33383regsgcc -march=k8 -Os -fomit-frame-pointer2014051920140517
33484regsgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2014051920140517
33542regsgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2014051920140517
33558regsgcc -fno-schedule-insns -O -fomit-frame-pointer2014051920140517
34607xmmgcc -m64 -march=k8 -Os -fomit-frame-pointer2014051920140517
34649xmmgcc -funroll-loops -m64 -Os -fomit-frame-pointer2014051920140517
34675regsgcc -m64 -march=nocona -Os -fomit-frame-pointer2014051920140517
34675regsgcc -march=nocona -Os -fomit-frame-pointer2014051920140517
35108regsgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2014051920140517
35259regsgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2014051920140517
36366regsgcc -O -fomit-frame-pointer2014051920140517
36367regsgcc -m64 -O -fomit-frame-pointer2014051920140517
36375regsgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2014051920140517
36375regsgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2014051920140517
36392regsgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2014051920140517
36400regsgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2014051920140517
36417regsgcc -m64 -march=core2 -O -fomit-frame-pointer2014051920140517
36500regsgcc -m64 -march=k8 -O -fomit-frame-pointer2014051920140517
36500regsgcc -march=k8 -O -fomit-frame-pointer2014051920140517
36575regsgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2014051920140517
36575regsgcc -funroll-loops -m64 -O -fomit-frame-pointer2014051920140517
36641regsgcc -funroll-loops -O -fomit-frame-pointer2014051920140517
37025regsgcc -m64 -march=nocona -O -fomit-frame-pointer2014051920140517
37042regsgcc -march=nocona -O -fomit-frame-pointer2014051920140517
37484xmmgcc -march=k8 -Os -fomit-frame-pointer2014051920140517
37491xmmgcc -Os -fomit-frame-pointer2014051920140517
37492xmmgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2014051920140517
37492xmmgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2014051920140517
37492xmmgcc -m64 -march=nocona -Os -fomit-frame-pointer2014051920140517
37492xmmgcc -march=nocona -Os -fomit-frame-pointer2014051920140517
37516xmmgcc -fno-schedule-insns -Os -fomit-frame-pointer2014051920140517
37517xmmgcc -m64 -Os -fomit-frame-pointer2014051920140517
37533xmmgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2014051920140517
37534xmmgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2014051920140517
37534xmmgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2014051920140517
37567xmmgcc -funroll-loops -Os -fomit-frame-pointer2014051920140517
40075regsgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2014051920140517
40167regsgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2014051920140517
40225regsgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2014051920140517
40325regsgcc -funroll-loops -O2 -fomit-frame-pointer2014051920140517
40409regsgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2014051920140517
40817regsgcc -fno-schedule-insns -O2 -fomit-frame-pointer2014051920140517
40825regsgcc -m64 -march=core2 -O2 -fomit-frame-pointer2014051920140517
41225regsgcc -m64 -march=k8 -O2 -fomit-frame-pointer2014051920140517
41250regsgcc -march=k8 -O2 -fomit-frame-pointer2014051920140517
41300regsgcc -O2 -fomit-frame-pointer2014051920140517
41358regsgcc -m64 -O2 -fomit-frame-pointer2014051920140517
41417regsgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2014051920140517
41433regsgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2014051920140517
41442regsgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2014051920140517
41450regsgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2014051920140517
41491regsgcc -funroll-loops -O3 -fomit-frame-pointer2014051920140517
41525regsgcc -m64 -march=k8 -O3 -fomit-frame-pointer2014051920140517
41533regsgcc -O3 -fomit-frame-pointer2014051920140517
41550regsgcc -m64 -O3 -fomit-frame-pointer2014051920140517
41625regsgcc -fno-schedule-insns -O3 -fomit-frame-pointer2014051920140517
41625regsgcc -m64 -march=core2 -O3 -fomit-frame-pointer2014051920140517
41625regsgcc -march=k8 -O3 -fomit-frame-pointer2014051920140517
42642regsgcc -m64 -march=nocona -O2 -fomit-frame-pointer2014051920140517
42658regsgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2014051920140517
42683regsgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2014051920140517
42725regsgcc -march=nocona -O2 -fomit-frame-pointer2014051920140517
43075regsgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2014051920140517
43100regsgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2014051920140517
43184regsgcc -march=nocona -O3 -fomit-frame-pointer2014051920140517
43192regsgcc -m64 -march=nocona -O3 -fomit-frame-pointer2014051920140517
116909regsgcc2014051920140517
116916regscc2014051920140517
116992regsgcc -funroll-loops2014051920140517
234450xmmgcc2014051920140517
234459xmmcc2014051920140517
234483xmmgcc -funroll-loops2014051920140517

Compiler output

Implementation: crypto_hash/blake2s/ref
Compiler: cc
blake2s-ref.c: blake2s-ref.c: In function 'blake2s_init0':
blake2s-ref.c: blake2s-ref.c:137: error: 'for' loop initial declaration used outside C99 mode
blake2s-ref.c: blake2s-ref.c: In function 'blake2s_init_param':
blake2s-ref.c: blake2s-ref.c:149: error: 'for' loop initial declaration used outside C99 mode
blake2s-ref.c: blake2s-ref.c: In function 'blake2s_compress':
blake2s-ref.c: blake2s-ref.c:215: error: 'for' loop initial declaration used outside C99 mode
blake2s-ref.c: blake2s-ref.c:218: error: redefinition of 'i'
blake2s-ref.c: blake2s-ref.c:215: error: previous definition of 'i' was here
blake2s-ref.c: blake2s-ref.c:218: error: 'for' loop initial declaration used outside C99 mode
blake2s-ref.c: blake2s-ref.c:262: error: redefinition of 'i'
blake2s-ref.c: blake2s-ref.c:218: error: previous definition of 'i' was here
blake2s-ref.c: blake2s-ref.c:262: error: 'for' loop initial declaration used outside C99 mode
blake2s-ref.c: blake2s-ref.c: In function 'blake2s_final':
blake2s-ref.c: blake2s-ref.c:318: error: 'for' loop initial declaration used outside C99 mode

Number of similar (compiler,implementation) pairs: 63, namely:
CompilerImplementations
cc ref
gcc ref
gcc -O2 -fomit-frame-pointer ref
gcc -O3 -fomit-frame-pointer ref
gcc -O -fomit-frame-pointer ref
gcc -Os -fomit-frame-pointer ref
gcc -fno-schedule-insns -O2 -fomit-frame-pointer ref
gcc -fno-schedule-insns -O3 -fomit-frame-pointer ref
gcc -fno-schedule-insns -O -fomit-frame-pointer ref
gcc -fno-schedule-insns -Os -fomit-frame-pointer ref
gcc -funroll-loops ref
gcc -funroll-loops -O2 -fomit-frame-pointer ref
gcc -funroll-loops -O3 -fomit-frame-pointer ref
gcc -funroll-loops -O -fomit-frame-pointer ref
gcc -funroll-loops -Os -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer ref
gcc -m64 -O2 -fomit-frame-pointer ref
gcc -m64 -O3 -fomit-frame-pointer ref
gcc -m64 -O -fomit-frame-pointer ref
gcc -m64 -Os -fomit-frame-pointer ref
gcc -m64 -march=core2 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core2 -O3 -fomit-frame-pointer ref
gcc -m64 -march=core2 -O -fomit-frame-pointer ref
gcc -m64 -march=core2 -Os -fomit-frame-pointer ref
gcc -m64 -march=k8 -O2 -fomit-frame-pointer ref
gcc -m64 -march=k8 -O3 -fomit-frame-pointer ref
gcc -m64 -march=k8 -O -fomit-frame-pointer ref
gcc -m64 -march=k8 -Os -fomit-frame-pointer ref
gcc -m64 -march=nocona -O2 -fomit-frame-pointer ref
gcc -m64 -march=nocona -O3 -fomit-frame-pointer ref
gcc -m64 -march=nocona -O -fomit-frame-pointer ref
gcc -m64 -march=nocona -Os -fomit-frame-pointer ref
gcc -march=k8 -O2 -fomit-frame-pointer ref
gcc -march=k8 -O3 -fomit-frame-pointer ref
gcc -march=k8 -O -fomit-frame-pointer ref
gcc -march=k8 -Os -fomit-frame-pointer ref
gcc -march=nocona -O2 -fomit-frame-pointer ref
gcc -march=nocona -O3 -fomit-frame-pointer ref
gcc -march=nocona -O -fomit-frame-pointer ref
gcc -march=nocona -Os -fomit-frame-pointer ref

Compiler output

Implementation: crypto_hash/blake2s/regs
Compiler: cc
blake2s.c: blake2s.c: In function 'crypto_hash_blake2s_regs':
blake2s.c: blake2s.c:796: warning: large integer implicitly truncated to unsigned type

Number of similar (compiler,implementation) pairs: 63, namely:
CompilerImplementations
cc regs
gcc regs
gcc -O2 -fomit-frame-pointer regs
gcc -O3 -fomit-frame-pointer regs
gcc -O -fomit-frame-pointer regs
gcc -Os -fomit-frame-pointer regs
gcc -fno-schedule-insns -O2 -fomit-frame-pointer regs
gcc -fno-schedule-insns -O3 -fomit-frame-pointer regs
gcc -fno-schedule-insns -O -fomit-frame-pointer regs
gcc -fno-schedule-insns -Os -fomit-frame-pointer regs
gcc -funroll-loops regs
gcc -funroll-loops -O2 -fomit-frame-pointer regs
gcc -funroll-loops -O3 -fomit-frame-pointer regs
gcc -funroll-loops -O -fomit-frame-pointer regs
gcc -funroll-loops -Os -fomit-frame-pointer regs
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer regs
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer regs
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer regs
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer regs
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer regs
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer regs
gcc -funroll-loops -m64 -O -fomit-frame-pointer regs
gcc -funroll-loops -m64 -Os -fomit-frame-pointer regs
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer regs
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer regs
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer regs
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer regs
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer regs
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer regs
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer regs
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer regs
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer regs
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer regs
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer regs
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer regs
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer regs
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer regs
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer regs
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer regs
gcc -m64 -O2 -fomit-frame-pointer regs
gcc -m64 -O3 -fomit-frame-pointer regs
gcc -m64 -O -fomit-frame-pointer regs
gcc -m64 -Os -fomit-frame-pointer regs
gcc -m64 -march=core2 -O2 -fomit-frame-pointer regs
gcc -m64 -march=core2 -O3 -fomit-frame-pointer regs
gcc -m64 -march=core2 -O -fomit-frame-pointer regs
gcc -m64 -march=core2 -Os -fomit-frame-pointer regs
gcc -m64 -march=k8 -O2 -fomit-frame-pointer regs
gcc -m64 -march=k8 -O3 -fomit-frame-pointer regs
gcc -m64 -march=k8 -O -fomit-frame-pointer regs
gcc -m64 -march=k8 -Os -fomit-frame-pointer regs
gcc -m64 -march=nocona -O2 -fomit-frame-pointer regs
gcc -m64 -march=nocona -O3 -fomit-frame-pointer regs
gcc -m64 -march=nocona -O -fomit-frame-pointer regs
gcc -m64 -march=nocona -Os -fomit-frame-pointer regs
gcc -march=k8 -O2 -fomit-frame-pointer regs
gcc -march=k8 -O3 -fomit-frame-pointer regs
gcc -march=k8 -O -fomit-frame-pointer regs
gcc -march=k8 -Os -fomit-frame-pointer regs
gcc -march=nocona -O2 -fomit-frame-pointer regs
gcc -march=nocona -O3 -fomit-frame-pointer regs
gcc -march=nocona -O -fomit-frame-pointer regs
gcc -march=nocona -Os -fomit-frame-pointer regs

Compiler output

Implementation: crypto_hash/blake2s/avxicc
Compiler: cc
blake2s.s: blake2s.s: Assembler messages:
blake2s.s: blake2s.s:16: Error: no such instruction: `vmovdqu .L_2il0floatpacket.10(%rip),%xmm4'
blake2s.s: blake2s.s:18: Error: no such instruction: `vmovdqu .L_2il0floatpacket.7(%rip),%xmm0'
blake2s.s: blake2s.s:19: Error: no such instruction: `vmovdqa %xmm4,%xmm2'
blake2s.s: blake2s.s:20: Error: no such instruction: `vmovdqu .L_2il0floatpacket.8(%rip),%xmm1'
blake2s.s: blake2s.s:22: Error: no such instruction: `vmovdqu .L_2il0floatpacket.9(%rip),%xmm3'
blake2s.s: blake2s.s:24: Error: no such instruction: `vmovdqu .L_2il0floatpacket.11(%rip),%xmm5'
blake2s.s: blake2s.s:39: Error: no such instruction: `vmovdqu (%rcx,%r9),%xmm9'
blake2s.s: blake2s.s:40: Error: no such instruction: `vmovdqu 16(%rcx,%r9),%xmm8'
blake2s.s: blake2s.s:41: Error: no such instruction: `vmovdqu 32(%rcx,%r9),%xmm7'
blake2s.s: ...
blake2s.s: blake2s.s:1246: Error: no such instruction: `vpxor %xmm1,%xmm3,%xmm6'
blake2s.s: blake2s.s:1247: Error: no such instruction: `vpsrld $7,%xmm8,%xmm3'
blake2s.s: blake2s.s:1248: Error: no such instruction: `vpslld $25,%xmm8,%xmm8'
blake2s.s: blake2s.s:1249: Error: no such instruction: `vpxor %xmm8,%xmm3,%xmm3'
blake2s.s: blake2s.s:1250: Error: no such instruction: `vpshufd $147,%xmm3,%xmm0'
blake2s.s: blake2s.s:1251: Error: no such instruction: `vpshufd $57,%xmm4,%xmm1'
blake2s.s: blake2s.s:1252: Error: no such instruction: `vpxor %xmm1,%xmm0,%xmm5'
blake2s.s: blake2s.s:1253: Error: no such instruction: `vpxor %xmm5,%xmm2,%xmm2'
blake2s.s: blake2s.s:1254: Error: no such instruction: `vmovdqu %xmm6,(%rdi)'
blake2s.s: blake2s.s:1255: Error: no such instruction: `vmovdqu %xmm2,16(%rdi)'

Number of similar (compiler,implementation) pairs: 63, namely:
CompilerImplementations
cc avxicc
gcc avxicc
gcc -O2 -fomit-frame-pointer avxicc
gcc -O3 -fomit-frame-pointer avxicc
gcc -O -fomit-frame-pointer avxicc
gcc -Os -fomit-frame-pointer avxicc
gcc -fno-schedule-insns -O2 -fomit-frame-pointer avxicc
gcc -fno-schedule-insns -O3 -fomit-frame-pointer avxicc
gcc -fno-schedule-insns -O -fomit-frame-pointer avxicc
gcc -fno-schedule-insns -Os -fomit-frame-pointer avxicc
gcc -funroll-loops avxicc
gcc -funroll-loops -O2 -fomit-frame-pointer avxicc
gcc -funroll-loops -O3 -fomit-frame-pointer avxicc
gcc -funroll-loops -O -fomit-frame-pointer avxicc
gcc -funroll-loops -Os -fomit-frame-pointer avxicc
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer avxicc
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer avxicc
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer avxicc
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -O -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -Os -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer avxicc
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer avxicc
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer avxicc
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer avxicc
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer avxicc
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer avxicc
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer avxicc
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer avxicc
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer avxicc
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer avxicc
gcc -m64 -O2 -fomit-frame-pointer avxicc
gcc -m64 -O3 -fomit-frame-pointer avxicc
gcc -m64 -O -fomit-frame-pointer avxicc
gcc -m64 -Os -fomit-frame-pointer avxicc
gcc -m64 -march=core2 -O2 -fomit-frame-pointer avxicc
gcc -m64 -march=core2 -O3 -fomit-frame-pointer avxicc
gcc -m64 -march=core2 -O -fomit-frame-pointer avxicc
gcc -m64 -march=core2 -Os -fomit-frame-pointer avxicc
gcc -m64 -march=k8 -O2 -fomit-frame-pointer avxicc
gcc -m64 -march=k8 -O3 -fomit-frame-pointer avxicc
gcc -m64 -march=k8 -O -fomit-frame-pointer avxicc
gcc -m64 -march=k8 -Os -fomit-frame-pointer avxicc
gcc -m64 -march=nocona -O2 -fomit-frame-pointer avxicc
gcc -m64 -march=nocona -O3 -fomit-frame-pointer avxicc
gcc -m64 -march=nocona -O -fomit-frame-pointer avxicc
gcc -m64 -march=nocona -Os -fomit-frame-pointer avxicc
gcc -march=k8 -O2 -fomit-frame-pointer avxicc
gcc -march=k8 -O3 -fomit-frame-pointer avxicc
gcc -march=k8 -O -fomit-frame-pointer avxicc
gcc -march=k8 -Os -fomit-frame-pointer avxicc
gcc -march=nocona -O2 -fomit-frame-pointer avxicc
gcc -march=nocona -O3 -fomit-frame-pointer avxicc
gcc -march=nocona -O -fomit-frame-pointer avxicc
gcc -march=nocona -Os -fomit-frame-pointer avxicc