Implementation notes: amd64, h5nano, crypto_stream/cryptmtv3

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_stream
Primitive: cryptmtv3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
8840	`e/v3`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141016	20141014
8840	`e/v3`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20141016	20141014
8840	`e/v3`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140629	20140622
8840	`e/v3`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140629	20140622
8980	`e/v3`	`clang -O3 -fomit-frame-pointer`	20140629	20140622
9230	`e/v3`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140511	20140425
9230	`e/v3`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140511	20140425
9230	`e/v3`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140511	20140425
9230	`e/v3`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140511	20140425
9245	`e/v3`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140511	20140425
9245	`e/v3`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140511	20140425
9310	`e/v3`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140511	20140425
9375	`e/v3`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140511	20140425
9375	`e/v3`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140511	20140425
9380	`e/v3`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140511	20140425
9380	`e/v3`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140511	20140425
9395	`e/v3`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140511	20140425
9395	`e/v3`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140511	20140425
9395	`e/v3`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140511	20140425
9395	`e/v3`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140511	20140425
9395	`e/v3`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140511	20140425
9400	`e/v3`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140511	20140425
9435	`e/v3`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140511	20140425
9435	`e/v3`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140511	20140425
9455	`e/v3`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140511	20140425
9455	`e/v3`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140511	20140425
9470	`e/v3`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140511	20140425
9470	`e/v3`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140511	20140425
9515	`e/v3`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140511	20140425
9530	`e/v3`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140511	20140425
9535	`e/v3`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140511	20140425
9540	`e/v3`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140511	20140425
9545	`e/v3`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140511	20140425
9545	`e/v3`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140511	20140425
9555	`e/v3`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140511	20140425
9555	`e/v3`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140511	20140425
9555	`e/v3`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140511	20140425
9555	`e/v3`	`gcc -march=nocona -O -fomit-frame-pointer`	20140511	20140425
9590	`e/v3`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140511	20140425
9590	`e/v3`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140511	20140425
9590	`e/v3`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140511	20140425
9595	`e/v3`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140511	20140425
9605	`e/v3`	`gcc -O -fomit-frame-pointer`	20140511	20140425
9605	`e/v3`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140511	20140425
9605	`e/v3`	`gcc -m64 -O -fomit-frame-pointer`	20140511	20140425
9605	`e/v3`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140511	20140425
9605	`e/v3`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140511	20140425
9605	`e/v3`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140511	20140425
9605	`e/v3`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140511	20140425
9605	`e/v3`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140511	20140425
9610	`e/v3`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140511	20140425
9610	`e/v3`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140511	20140425
9610	`e/v3`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140511	20140425
9615	`e/v3`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140511	20140425
9615	`e/v3`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140511	20140425
9615	`e/v3`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140511	20140425
9615	`e/v3`	`gcc -march=k8 -O -fomit-frame-pointer`	20140511	20140425
9620	`e/v3`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140511	20140425
9625	`e/v3`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140511	20140425
9625	`e/v3`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140511	20140425
9625	`e/v3`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140511	20140425
9625	`e/v3`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140511	20140425
9625	`e/v3`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140511	20140425
9625	`e/v3`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140511	20140425
9630	`e/v3`	`gcc -O3 -fomit-frame-pointer`	20140511	20140425
9630	`e/v3`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140511	20140425
9630	`e/v3`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140511	20140425
9630	`e/v3`	`gcc -m64 -O3 -fomit-frame-pointer`	20140511	20140425
9630	`e/v3`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140511	20140425
9630	`e/v3`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140511	20140425
9635	`e/v3`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140511	20140425
9640	`e/v3`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140511	20140425
9640	`e/v3`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140511	20140425
9650	`e/v3`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140511	20140425
9655	`e/v3`	`gcc -O2 -fomit-frame-pointer`	20140511	20140425
9655	`e/v3`	`gcc -m64 -O2 -fomit-frame-pointer`	20140511	20140425
9670	`e/v3`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140511	20140425
9680	`e/v3`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140511	20140425
9680	`e/v3`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140511	20140425
9680	`e/v3`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140511	20140425
9680	`e/v3`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140511	20140425
9680	`e/v3`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140511	20140425
9700	`e/v3`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140511	20140425
9990	`e/v3`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140511	20140425
9990	`e/v3`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140511	20140425
10010	`e/v3`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140511	20140425
10030	`e/v3`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140511	20140425
10030	`e/v3`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140511	20140425
10035	`e/v3`	`gcc -Os -fomit-frame-pointer`	20140511	20140425
10035	`e/v3`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140511	20140425
10035	`e/v3`	`gcc -m64 -Os -fomit-frame-pointer`	20140511	20140425
10035	`e/v3`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140511	20140425
10035	`e/v3`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140511	20140425
10040	`e/v3`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140511	20140425
10040	`e/v3`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140511	20140425
10160	`e/v3`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140511	20140425
10160	`e/v3`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140511	20140425
62590	`e/v3`	`cc`	20140511	20140425
62720	`e/v3`	`gcc -funroll-loops`	20140511	20140425
62795	`e/v3`	`gcc`	20140511	20140425

Compiler output

Implementation: crypto_stream/cryptmtv3/e/v3
Compiler: clang -O3 -fomit-frame-pointer

cryptmt-v3.c: In file included from cryptmt-v3.c:1:
cryptmt-v3.c: ./e/cryptmt-v3.c:189:18: warning: array index of '156' indexes past the end of an array (that contains 156 elements) [-Warray-bounds]
cryptmt-v3.c: do_recursion(ps->gt;sfmt[N], ps->gt;sfmt[POS1], ps->gt;sfmt[N - 1]);
cryptmt-v3.c: ^ ~
cryptmt-v3.c: ./e/cryptmt-v3.c:25:5: note: array 'sfmt' declared here
cryptmt-v3.c: u32 sfmt[N][4];
cryptmt-v3.c: ^
cryptmt-v3.c: ./e/cryptmt-v3.c:403:27: warning: argument to 'sizeof' in 'memset' call is the same expression as the destination; did you mean to dereference it? [-Wsizeof-pointer-memaccess]
cryptmt-v3.c: memset(ctx, 0, sizeof(ctx));
cryptmt-v3.c: ~~~ ^~~
cryptmt-v3.c: 2 warnings generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer	e/v3

Compiler output

Implementation: crypto_stream/cryptmtv3/e/v3
Compiler: clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer

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

Compiler	Implementations
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer	e/v3

Compiler output

Implementation: crypto_stream/cryptmtv3/e/v3
Compiler: clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer

api.c: clang: warning: argument unused during compilation: '-mcpu=core-avx2'
api.c: clang: warning: argument unused during compilation: '-mavx2'
api.c: clang: warning: argument unused during compilation: '-mpclmul'
api.c: clang: warning: argument unused during compilation: '-fpolly'
api.c: clang: warning: argument unused during compilation: '-fvectorize'
api.c: clang: warning: argument unused during compilation: '-fslp-vectorize'
api.c: clang: warning: argument unused during compilation: '-fslp-vectorize-aggressive'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-mcpu=core-avx2'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-mavx2'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-mpclmul'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-fpolly'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-fvectorize'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-fslp-vectorize'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-fslp-vectorize-aggressive'
cryptmt-v3.c: In file included from cryptmt-v3.c:1:
cryptmt-v3.c: ./e/cryptmt-v3.c:189:18: warning: array index of '156' indexes past the end of an array (that contains 156 elements) [-Warray-bounds]
cryptmt-v3.c: do_recursion(ps->gt;sfmt[N], ps->gt;sfmt[POS1], ps->gt;sfmt[N - 1]);
cryptmt-v3.c: ^ ~
cryptmt-v3.c: ./e/cryptmt-v3.c:25:5: note: array 'sfmt' declared here
cryptmt-v3.c: u32 sfmt[N][4];
cryptmt-v3.c: ^
cryptmt-v3.c: ./e/cryptmt-v3.c:403:27: warning: argument to 'sizeof' in 'memset' call is the same expression as the destination; did you mean to dereference it? [-Wsizeof-pointer-memaccess]
cryptmt-v3.c: memset(ctx, 0, sizeof(ctx));
cryptmt-v3.c: ~~~ ^~~
cryptmt-v3.c: 2 warnings generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.

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

Compiler	Implementations
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer	e/v3

Compiler output

Implementation: crypto_stream/cryptmtv3/e/v3
Compiler: clang -O3 -fwrapv -mavx2 -fomit-frame-pointer

api.c: clang: warning: argument unused during compilation: '-mavx2'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-mavx2'
cryptmt-v3.c: In file included from cryptmt-v3.c:1:
cryptmt-v3.c: ./e/cryptmt-v3.c:189:18: warning: array index of '156' indexes past the end of an array (that contains 156 elements) [-Warray-bounds]
cryptmt-v3.c: do_recursion(ps->gt;sfmt[N], ps->gt;sfmt[POS1], ps->gt;sfmt[N - 1]);
cryptmt-v3.c: ^ ~
cryptmt-v3.c: ./e/cryptmt-v3.c:25:5: note: array 'sfmt' declared here
cryptmt-v3.c: u32 sfmt[N][4];
cryptmt-v3.c: ^
cryptmt-v3.c: ./e/cryptmt-v3.c:403:27: warning: argument to 'sizeof' in 'memset' call is the same expression as the destination; did you mean to dereference it? [-Wsizeof-pointer-memaccess]
cryptmt-v3.c: memset(ctx, 0, sizeof(ctx));
cryptmt-v3.c: ~~~ ^~~
cryptmt-v3.c: 2 warnings generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.

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

Compiler	Implementations
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer	e/v3

Compiler output

Implementation: crypto_stream/cryptmtv3/e/v3
Compiler: clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer

api.c: clang: warning: argument unused during compilation: '-mavx2'
api.c: clang: warning: argument unused during compilation: '-fpolly'
api.c: clang: warning: argument unused during compilation: '-fvectorize'
api.c: clang: warning: argument unused during compilation: '-fslp-vectorize'
api.c: clang: warning: argument unused during compilation: '-fslp-vectorize-aggressive'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-mavx2'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-fpolly'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-fvectorize'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-fslp-vectorize'
cryptmt-v3.c: clang: warning: argument unused during compilation: '-fslp-vectorize-aggressive'
cryptmt-v3.c: In file included from cryptmt-v3.c:1:
cryptmt-v3.c: ./e/cryptmt-v3.c:189:18: warning: array index of '156' indexes past the end of an array (that contains 156 elements) [-Warray-bounds]
cryptmt-v3.c: do_recursion(ps->gt;sfmt[N], ps->gt;sfmt[POS1], ps->gt;sfmt[N - 1]);
cryptmt-v3.c: ^ ~
cryptmt-v3.c: ./e/cryptmt-v3.c:25:5: note: array 'sfmt' declared here
cryptmt-v3.c: u32 sfmt[N][4];
cryptmt-v3.c: ^
cryptmt-v3.c: ./e/cryptmt-v3.c:403:27: warning: argument to 'sizeof' in 'memset' call is the same expression as the destination; did you mean to dereference it? [-Wsizeof-pointer-memaccess]
cryptmt-v3.c: memset(ctx, 0, sizeof(ctx));
cryptmt-v3.c: ~~~ ^~~
cryptmt-v3.c: 2 warnings generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.

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

Compiler	Implementations
clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer	e/v3