Implementation notes: amd64, sand, crypto_stream/simon64128ctr

Computer: sand
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20171218
Operation: crypto_stream
Primitive: simon64128ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
6820? ? ?? ? ?sse4clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2018041420171218
6828? ? ?? ? ?sse4clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2018041420171218

Compiler output

Implementation: crypto_stream/simon64128ctr/avx2
Compiler: cc
stream.c: stream.c:147:3: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'Encrypt' that is compiled without support for 'sse4.2'
stream.c: SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:24:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:23:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c: ^
stream.c: stream.c:147:24: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'Encrypt' that is compiled without support for 'sse4.2'
stream.c: SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:25:22: note: expanded from macro 'SET8'
stream.c: #define SET8(X,c) (X=SET(c,c,c,c,c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:23:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c: ^
stream.c: stream.c:147:24: error: always_inline function '_mm256_add_epi32' requires target feature 'avx2', but would be inlined into function 'Encrypt' that is compiled without support for 'avx2'
stream.c: ./Intrinsics_AVX2_64block.h:25:46: note: expanded from macro 'SET8'
stream.c: #define SET8(X,c) (X=SET(c,c,c,c,c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:16:13: note: expanded from macro 'ADD'
stream.c: #define ADD _mm256_add_epi32
stream.c: ^
stream.c: ...
Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
cc avx2
clang -O3 -fomit-frame-pointer -Qunused-arguments avx2
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2

Compiler output

Implementation: crypto_stream/simon64128ctr/sse4
Compiler: cc
stream.c: stream.c:340:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'ExpandKeyBS' that is compiled without support for 'ssse3'
stream.c: EKBS(rk);
stream.c: ^
stream.c: ./Simon64128SSE4.h:64:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,4,_D), RKBS(rk,5,_D), RKBS(rk,6,_C), RKBS(rk,7,_D), RKBS(rk,8,_D), RKBS(rk,9,_C), RKBS(rk,10,_D), RKBS(rk,11,_D), \
stream.c: ^
stream.c: ./Simon64128SSE4.h:53:52: note: expanded from macro 'RKBS'
stream.c: #define RKBS(rk,r,_V) (rk[r][7]= _D ^ rk[r-4][7] ^ ROR8(rk[r-1][2]) ^ rk[r-3][7] ^ ROR8(rk[r-1][3]) ^ ROR8(rk[r-3][0]), \
stream.c: ^
stream.c: ./Intrinsics_SSE4_64block.h:39:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X) (SHFL(X,R8))
stream.c: ^
stream.c: ./Intrinsics_SSE4_64block.h:34:14: note: expanded from macro 'SHFL'
stream.c: #define SHFL _mm_shuffle_epi8
stream.c: ^
stream.c: stream.c:340:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'ExpandKeyBS' that is compiled without support for 'ssse3'
stream.c: ./Simon64128SSE4.h:64:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,4,_D), RKBS(rk,5,_D), RKBS(rk,6,_C), RKBS(rk,7,_D), RKBS(rk,8,_D), RKBS(rk,9,_C), RKBS(rk,10,_D), RKBS(rk,11,_D), \
stream.c: ^
stream.c: ./Simon64128SSE4.h:53:85: note: expanded from macro 'RKBS'
stream.c: #define RKBS(rk,r,_V) (rk[r][7]= _D ^ rk[r-4][7] ^ ROR8(rk[r-1][2]) ^ rk[r-3][7] ^ ROR8(rk[r-1][3]) ^ ROR8(rk[r-3][0]), \
stream.c: ^
stream.c: ./Intrinsics_SSE4_64block.h:39:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X) (SHFL(X,R8))
stream.c: ^
stream.c: ...
Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
cc sse4
clang -O3 -fomit-frame-pointer -Qunused-arguments sse4
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse4
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse4
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse4

Compiler output

Implementation: crypto_stream/simon64128ctr/avx2
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:147:3: error: always_inline function '_mm256_set_epi32' requires target feature 'xsave', but would be inlined into function 'Encrypt' that is compiled without support for 'xsave'
stream.c: SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:24:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:23:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c: ^
stream.c: stream.c:147:24: error: always_inline function '_mm256_set_epi32' requires target feature 'xsave', but would be inlined into function 'Encrypt' that is compiled without support for 'xsave'
stream.c: SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:25:22: note: expanded from macro 'SET8'
stream.c: #define SET8(X,c) (X=SET(c,c,c,c,c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:23:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c: ^
stream.c: stream.c:147:24: error: always_inline function '_mm256_add_epi32' requires target feature 'xsave', but would be inlined into function 'Encrypt' that is compiled without support for 'xsave'
stream.c: ./Intrinsics_AVX2_64block.h:25:46: note: expanded from macro 'SET8'
stream.c: #define SET8(X,c) (X=SET(c,c,c,c,c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:16:13: note: expanded from macro 'ADD'
stream.c: #define ADD _mm256_add_epi32
stream.c: ^
stream.c: ...
Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2

Compiler output

Implementation: crypto_stream/simon64128ctr/sse4
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
try.c: /tmp/try-anything-6d77a3.o: In function `alignedcalloc':
try.c: try-anything.c:(.text+0x...): warning: random() may return deterministic values, is that what you want?
try.c: /tmp/try-anything-749b8a.o: In function `alignedcalloc':
try.c: try-anything.c:(.text+0x...): warning: random() may return deterministic values, is that what you want?
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments sse4

Compiler output

Implementation: crypto_stream/simon64128ctr/sse4
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments
try.c: /tmp/try-anything-7f4841.o: In function `alignedcalloc':
try.c: try-anything.c:(.text+0x...): warning: random() may return deterministic values, is that what you want?
try.c: /tmp/try-anything-1a7c32.o: In function `alignedcalloc':
try.c: try-anything.c:(.text+0x...): warning: random() may return deterministic values, is that what you want?
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse4

Compiler output

Implementation: crypto_stream/simon64128ctr/avx2
Compiler: gcc
stream.c: In file included from Simon64128AVX2.h:17,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:5:23: error: immintrin.h: No such file or directory
stream.c: stream.c:23: error: expected declaration specifiers or '...' before '__m256i'
stream.c: stream.c:25: error: expected declaration specifiers or '...' before '__m256i'
stream.c: stream.c:26: error: expected declaration specifiers or '...' before '__m256i'
stream.c: stream.c:27: error: expected declaration specifiers or '...' before '__m256i'
stream.c: stream.c:28: error: expected ')' before 'M'
stream.c: stream.c: In function 'crypto_stream_simon64128ctr_avx2':
stream.c: stream.c:42: error: '__m256i' undeclared (first use in this function)
stream.c: stream.c:42: error: (Each undeclared identifier is reported only once
stream.c: stream.c:42: error: for each function it appears in.)
stream.c: stream.c:42: error: expected ';' before 'rk'
stream.c: stream.c:52: error: 'rk' undeclared (first use in this function)
stream.c: stream.c:52: error: too many arguments to function 'ExpandKeyBS'
stream.c: stream.c:55: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: stream.c:55: error: too many arguments to function 'Encrypt'
stream.c: stream.c:62: error: too many arguments to function 'ExpandKeyNBS'
stream.c: stream.c:65: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: stream.c:65: error: too many arguments to function 'Encrypt'
stream.c: stream.c:70: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: stream.c:70: error: too many arguments to function 'Encrypt'
stream.c: stream.c:75: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: stream.c:75: error: too many arguments to function 'Encrypt'
stream.c: stream.c:80: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: ...
Number of similar (compiler,implementation) pairs: 66, namely:
CompilerImplementations
gcc avx2
gcc -O2 -fomit-frame-pointer avx2
gcc -O3 -fomit-frame-pointer avx2
gcc -O -fomit-frame-pointer avx2
gcc -Os -fomit-frame-pointer avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer avx2
gcc -funroll-loops avx2
gcc -funroll-loops -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -O -fomit-frame-pointer avx2
gcc -funroll-loops -Os -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer avx2
gcc -m64 -O2 -fomit-frame-pointer avx2
gcc -m64 -O3 -fomit-frame-pointer avx2
gcc -m64 -O -fomit-frame-pointer avx2
gcc -m64 -Os -fomit-frame-pointer avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer avx2
gcc -march=k8 -O2 -fomit-frame-pointer avx2
gcc -march=k8 -O3 -fomit-frame-pointer avx2
gcc -march=k8 -O -fomit-frame-pointer avx2
gcc -march=k8 -Os -fomit-frame-pointer avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv avx2
gcc -march=nocona -O2 -fomit-frame-pointer avx2
gcc -march=nocona -O3 -fomit-frame-pointer avx2
gcc -march=nocona -O -fomit-frame-pointer avx2
gcc -march=nocona -Os -fomit-frame-pointer avx2

Compiler output

Implementation: crypto_stream/simon64128ctr/sse4
Compiler: gcc
stream.c: In file included from Simon64128SSE4.h:17,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:5:23: error: smmintrin.h: No such file or directory
stream.c: stream.c:24: error: expected declaration specifiers or '...' before '__m128i'
stream.c: stream.c:26: error: expected declaration specifiers or '...' before '__m128i'
stream.c: stream.c:27: error: expected declaration specifiers or '...' before '__m128i'
stream.c: stream.c:28: error: expected declaration specifiers or '...' before '__m128i'
stream.c: stream.c:29: error: expected ')' before 'M'
stream.c: stream.c: In function 'crypto_stream_simon64128ctr_sse4':
stream.c: stream.c:42: error: '__m128i' undeclared (first use in this function)
stream.c: stream.c:42: error: (Each undeclared identifier is reported only once
stream.c: stream.c:42: error: for each function it appears in.)
stream.c: stream.c:42: error: expected ';' before 'rk'
stream.c: stream.c:54: error: 'rk' undeclared (first use in this function)
stream.c: stream.c:54: error: too many arguments to function 'ExpandKeyBS'
stream.c: stream.c:57: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: stream.c:57: error: too many arguments to function 'Encrypt'
stream.c: stream.c:64: error: too many arguments to function 'ExpandKeyNBS'
stream.c: stream.c:67: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: stream.c:67: error: too many arguments to function 'Encrypt'
stream.c: stream.c:72: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: stream.c:72: error: too many arguments to function 'Encrypt'
stream.c: stream.c:77: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: stream.c:77: error: too many arguments to function 'Encrypt'
stream.c: stream.c:82: warning: passing argument 4 of 'Encrypt' makes integer from pointer without a cast
stream.c: ...
Number of similar (compiler,implementation) pairs: 66, namely:
CompilerImplementations
gcc sse4
gcc -O2 -fomit-frame-pointer sse4
gcc -O3 -fomit-frame-pointer sse4
gcc -O -fomit-frame-pointer sse4
gcc -Os -fomit-frame-pointer sse4
gcc -fno-schedule-insns -O2 -fomit-frame-pointer sse4
gcc -fno-schedule-insns -O3 -fomit-frame-pointer sse4
gcc -fno-schedule-insns -O -fomit-frame-pointer sse4
gcc -fno-schedule-insns -Os -fomit-frame-pointer sse4
gcc -funroll-loops sse4
gcc -funroll-loops -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -O -fomit-frame-pointer sse4
gcc -funroll-loops -Os -fomit-frame-pointer sse4
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer sse4
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -O -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -Os -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer sse4
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer sse4
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer sse4
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer sse4
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer sse4
gcc -m64 -O2 -fomit-frame-pointer sse4
gcc -m64 -O3 -fomit-frame-pointer sse4
gcc -m64 -O -fomit-frame-pointer sse4
gcc -m64 -Os -fomit-frame-pointer sse4
gcc -m64 -march=k8 -O2 -fomit-frame-pointer sse4
gcc -m64 -march=k8 -O3 -fomit-frame-pointer sse4
gcc -m64 -march=k8 -O -fomit-frame-pointer sse4
gcc -m64 -march=k8 -Os -fomit-frame-pointer sse4
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer sse4
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer sse4
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer sse4
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer sse4
gcc -m64 -march=nocona -O2 -fomit-frame-pointer sse4
gcc -m64 -march=nocona -O3 -fomit-frame-pointer sse4
gcc -m64 -march=nocona -O -fomit-frame-pointer sse4
gcc -m64 -march=nocona -Os -fomit-frame-pointer sse4
gcc -march=k8 -O2 -fomit-frame-pointer sse4
gcc -march=k8 -O3 -fomit-frame-pointer sse4
gcc -march=k8 -O -fomit-frame-pointer sse4
gcc -march=k8 -Os -fomit-frame-pointer sse4
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv sse4
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv sse4
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv sse4
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv sse4
gcc -march=nocona -O2 -fomit-frame-pointer sse4
gcc -march=nocona -O3 -fomit-frame-pointer sse4
gcc -march=nocona -O -fomit-frame-pointer sse4
gcc -march=nocona -Os -fomit-frame-pointer sse4