Implementation notes: amd64, panther, crypto_kem/kyber1024

Computer: panther
Microarchitecture: amd64; Tiger Lake (806c1)
Architecture: amd64
CPU ID: GenuineIntel-000806c1-00-bfebfbff
SUPERCOP version: 20240425
Operation: crypto_kem
Primitive: kyber1024
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
10713592847 0 0115003 828 1752avx2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
107306113062 0 0138301 836 1752avx2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
107668115045 0 0140301 836 1752avx2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
115840125007 0 0150536 788 1784avx2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
11607494313 0 0116987 828 1752avx2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
12008496621 0 0118528 780 1752avx2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
121676102035 0 0125520 788 1784avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
12397497365 0 0120320 788 1784avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
54193954144 0 0104712 788 1784compactgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
59579013167 0 035467 828 1752refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
59669765580 0 0115781 836 1752compactclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
59932734909 0 059565 836 1752refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
60633641445 0 066117 836 1752refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
62724438880 0 089165 836 1752compactclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
63354440082 0 065640 788 1784refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
63932232749 0 057869 836 1752refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
67233142960 0 092757 836 1752compactclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
6751667038 0 054355 828 1752compactclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
69384513381 0 037016 788 1784refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
7145365943 0 054456 788 1784compactgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
72146412185 0 035240 788 1784refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
76056711533 0 033496 780 1752refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
80727513412 0 036275 828 1752refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425
8144826035 0 054136 788 1784compactgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
8466095243 0 052208 780 1752compactgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042920240425
8987947595 0 055595 828 1752compactclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042920240425

Compiler output

Implementation: avx2
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
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_kyber1024_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_kyber1024_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 (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx2