Implementation notes: amd64, bolero, crypto_kem/nhcompact512cca

Computer: bolero
Microarchitecture: amd64; Broadwell+AES (406f1)
Architecture: amd64
CPU ID: GenuineIntel-000406f1-1fc9cbf5
SUPERCOP version: 20240716
Operation: crypto_kem
Primitive: nhcompact512cca

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
113080	208204 0 0	227429 792 1608	`T:avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
118812	143872 0 0	163196 824 1576	`T:avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
120688	138516 0 0	157516 824 1576	`T:avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
127620	119330 0 0	136358 816 1640	`T:avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
147624	121378 0 0	138757 792 1608	`T:avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
154024	120818 0 0	137132 824 1576	`T:avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
164688	118803 0 0	134693 784 1576	`T:avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
171228	119311 0 0	136309 792 1608	`T:avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716

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 '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 '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
`T:avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Namespace violations

KeccakP-1600-times4-SIMD256.o KeccakF1600times4_FastLoop_Absorb T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_12rounds_FastLoop_Absorb T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_AddBytes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_AddLanesAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractAndAddBytes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractAndAddLanesAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractBytes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractLanesAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_InitializeAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_OverwriteBytes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_OverwriteLanesAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_OverwriteWithZeroes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_PermuteAll_12rounds T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_PermuteAll_24rounds T
ccakem.o crypto_kem_dec T
ccakem.o crypto_kem_enc T
ccakem.o crypto_kem_keypair T
consts.o _16xfhi R
consts.o _16xflo R
consts.o _16xmask R
consts.o _16xmontsqhi R
consts.o _16xmontsqlo R
consts.o _16xq R
consts.o _16xqinv R
consts.o _16xv R
consts.o zetas_exp R
consts.o zetas_inv_exp R
cpakem.o crypto_kem_dec T
cpakem.o crypto_kem_enc T
cpakem.o crypto_kem_keypair T
cpapke.o cpapke_dec T
cpapke.o cpapke_enc T
cpapke.o cpapke_keypair T
fips202.o KeccakF1600_StatePermute T
fips202.o shake128_absorb T
fips202.o shake128_squeezeblocks T
fips202.o shake256 T
fips202x4.o shake128x4 T
fips202x4.o shake256x4 T
ntt.o _16xq R
ntt.o _16xqinv R
ntt.o _16xv R
ntt.o basemul T
ntt.o invntt T
ntt.o ntt T
ntt.o zetas R
ntt.o zetas_exp R
ntt.o zetas_inv_exp R
nttasm.o invntt_avx T
nttasm.o ntt_avx T
poly.o poly_add T
poly.o poly_basemul T
poly.o poly_compress T
poly.o poly_decompress T
poly.o poly_frombytes T
poly.o poly_frommsg T
poly.o poly_invntt T
poly.o poly_ntt T
poly.o poly_sample T
poly.o poly_sub T
poly.o poly_tobytes T
poly.o poly_tomsg T
poly.o poly_uniform T
reduce.o barrett_reduce T
reduce.o montgomery_reduce T
verify.o cmov T
verify.o verify T

Number of similar (implementation,compiler) pairs: 8, namely:

Implementation	Compiler
`T:avx2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`T:avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`T:avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`T:avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`T:avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`T:avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`T:avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`T:avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`