Implementation notes: amd64, speed2supercop, crypto_kem/kyber768
Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: kyber768
| Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
|---|
| 103812 | 145358 0 0 | 167181 800 1568 | avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 106144 | 127295 0 0 | 145815 792 1632 | avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 109628 | 154415 0 0 | 175301 760 1600 | avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 114952 | 128902 0 0 | 147861 760 1600 | avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 116244 | 142664 0 0 | 164293 800 1568 | avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 116696 | 126047 0 0 | 144661 760 1600 | avx2 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 119452 | 125694 0 0 | 143245 752 1568 | avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 120528 | 133013 0 0 | 150757 800 1568 | avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 352692 | 97559 0 0 | 126885 800 1568 | compact | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 376492 | 42959 0 0 | 73077 800 1568 | compact | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 410520 | 54896 0 0 | 84549 760 1600 | compact | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 456852 | 56031 0 0 | 85478 800 1568 | compact | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 483904 | 47349 0 0 | 69461 800 1568 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 496328 | 6838 0 0 | 34847 792 1632 | compact | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 505796 | 33511 0 0 | 54917 800 1568 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 508168 | 31183 0 0 | 51998 800 1568 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 510080 | 43446 0 0 | 64261 760 1600 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 517812 | 8618 0 0 | 35758 800 1568 | compact | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 521240 | 7839 0 0 | 35525 760 1600 | compact | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 523196 | 12234 0 0 | 31175 792 1632 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 533656 | 14557 0 0 | 32814 800 1568 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 545380 | 13548 0 0 | 32317 760 1600 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 605988 | 12097 0 0 | 30589 760 1600 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 646644 | 5999 0 0 | 33469 760 1600 | compact | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 652456 | 11086 0 0 | 28485 752 1568 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
| 820256 | 5031 0 0 | 31365 752 1568 | compact | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240711 | 20240625 |
Compiler output
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_kem_kyber768_avx2_constbranchindex_KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_kem_kyber768_avx2_constbranchindex_KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:136:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: lanes1 = LOAD256u( curData1[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:136:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
Compiler output
kem.c: kem.c:24:32: warning: argument 1 of type 'uint8_t[1184]' {aka 'unsigned char[1184]'} with mismatched bound [-Warray-parameter=]
kem.c: 24 | int crypto_kem_keypair(uint8_t pk[KYBER_PUBLICKEYBYTES],
kem.c: | ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
kem.c: In file included from kem.c:5:
kem.c: kem.h:33:33: note: previously declared as 'uint8_t *' {aka 'unsigned char *'}
kem.c: 33 | int crypto_kem_keypair(uint8_t *pk, uint8_t *sk);
kem.c: | ~~~~~~~~~^~
kem.c: kem.c:25:32: warning: argument 2 of type 'uint8_t[2400]' {aka 'unsigned char[2400]'} with mismatched bound [-Warray-parameter=]
kem.c: 25 | uint8_t sk[KYBER_SECRETKEYBYTES])
kem.c: | ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
kem.c: kem.h:33:46: note: previously declared as 'uint8_t *' {aka 'unsigned char *'}
kem.c: 33 | int crypto_kem_keypair(uint8_t *pk, uint8_t *sk);
kem.c: | ~~~~~~~~~^~
kem.c: kem.c:50:28: warning: argument 1 of type 'uint8_t[1088]' {aka 'unsigned char[1088]'} with mismatched bound [-Warray-parameter=]
kem.c: 50 | int crypto_kem_enc(uint8_t ct[KYBER_CIPHERTEXTBYTES],
kem.c: | ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~
kem.c: kem.h:36:29: note: previously declared as 'uint8_t *' {aka 'unsigned char *'}
kem.c: 36 | int crypto_kem_enc(uint8_t *ct, uint8_t *ss, const uint8_t *pk);
kem.c: | ~~~~~~~~~^~
kem.c: kem.c:51:28: warning: argument 2 of type 'uint8_t[32]' {aka 'unsigned char[32]'} with mismatched bound [-Warray-parameter=]
kem.c: 51 | uint8_t ss[KYBER_SSBYTES],
kem.c: | ~~~~~~~~^~~~~~~~~~~~~~~~~
kem.c: kem.h:36:42: note: previously declared as 'uint8_t *' {aka 'unsigned char *'}
kem.c: 36 | int crypto_kem_enc(uint8_t *ct, uint8_t *ss, const uint8_t *pk);
kem.c: | ~~~~~~~~~^~
kem.c: ...
poly.c: poly.c:407:42: warning: argument 5 of type 'const uint8_t[32]' {aka 'const unsigned char[32]'} with mismatched bound [-Warray-parameter=]
poly.c: 407 | const uint8_t seed[32],
poly.c: | ~~~~~~~~~~~~~~^~~~~~~~
poly.c: In file included from poly.c:6:
poly.c: poly.h:37:43: note: previously declared as 'const uint8_t *' {aka 'const unsigned char *'}
poly.c: 37 | const uint8_t *seed,
poly.c: | ~~~~~~~~~~~~~~~^~~~
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
Compiler output
kem.c: kem.c:23:32: warning: argument 1 of type 'uint8_t[1184]' {aka 'unsigned char[1184]'} with mismatched bound [-Warray-parameter=]
kem.c: 23 | int crypto_kem_keypair(uint8_t pk[KYBER_PUBLICKEYBYTES],
kem.c: | ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
kem.c: In file included from kem.c:4:
kem.c: kem.h:33:33: note: previously declared as 'uint8_t *' {aka 'unsigned char *'}
kem.c: 33 | int crypto_kem_keypair(uint8_t *pk, uint8_t *sk);
kem.c: | ~~~~~~~~~^~
kem.c: kem.c:24:32: warning: argument 2 of type 'uint8_t[2400]' {aka 'unsigned char[2400]'} with mismatched bound [-Warray-parameter=]
kem.c: 24 | uint8_t sk[KYBER_SECRETKEYBYTES])
kem.c: | ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
kem.c: kem.h:33:46: note: previously declared as 'uint8_t *' {aka 'unsigned char *'}
kem.c: 33 | int crypto_kem_keypair(uint8_t *pk, uint8_t *sk);
kem.c: | ~~~~~~~~~^~
kem.c: kem.c:51:28: warning: argument 1 of type 'uint8_t[1088]' {aka 'unsigned char[1088]'} with mismatched bound [-Warray-parameter=]
kem.c: 51 | int crypto_kem_enc(uint8_t ct[KYBER_CIPHERTEXTBYTES],
kem.c: | ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~
kem.c: kem.h:36:29: note: previously declared as 'uint8_t *' {aka 'unsigned char *'}
kem.c: 36 | int crypto_kem_enc(uint8_t *ct, uint8_t *ss, const uint8_t *pk);
kem.c: | ~~~~~~~~~^~
kem.c: kem.c:52:28: warning: argument 2 of type 'uint8_t[32]' {aka 'unsigned char[32]'} with mismatched bound [-Warray-parameter=]
kem.c: 52 | uint8_t ss[KYBER_SSBYTES],
kem.c: | ~~~~~~~~^~~~~~~~~~~~~~~~~
kem.c: kem.h:36:42: note: previously declared as 'uint8_t *' {aka 'unsigned char *'}
kem.c: 36 | int crypto_kem_enc(uint8_t *ct, uint8_t *ss, const uint8_t *pk);
kem.c: | ~~~~~~~~~^~
kem.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| ref | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| ref | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
Passed TIMECOP
TIMECOP iterations: 1
Number of similar (implementation,compiler) pairs: 26, namely:
| Implementation | Compiler |
| avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| compact | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| compact | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| compact | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| compact | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| compact | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| compact | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| compact | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| compact | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| compact | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| ref | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| ref | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| ref | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| ref | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| ref | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |