Implementation notes: amd64, gcc14, crypto_kem/mceliece460896

Computer: gcc14
Architecture: amd64
CPU ID: GenuineIntel-00010676-bfebfbff
SUPERCOP version: 20220506
Operation: crypto_kem
Primitive: mceliece460896
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
321741476685 0 0168659 828 1712vecclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
322642176030 0 0167179 828 1712vecclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
322897276030 0 0167179 828 1712vecclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
342212876030 0 0168083 828 1712vecclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
347395355666 0 0145637 820 1712vecclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
355680268327 0 0159446 852 1744vecgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2021110820211108
362242368775 0 0160366 852 1744vecgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2021110820211108
373293152637 0 0142814 844 1712vecgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2021110820211108
26858993728983 0 0120115 828 1712refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
26860393528983 0 0120115 828 1712refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
26888206328951 0 0121019 828 1712refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
26926083530811 0 0122811 828 1712refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
29395887329930 0 0123336 860 1744refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2021110820211108
33103089613354 0 0103413 820 1712refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2021110820211108
38697825811907 0 0102070 844 1712refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2021110820211108
38855173515227 0 0106782 852 1744refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2021110820211108
39237290715007 0 0106158 852 1744refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2021110820211108

Test failure

Implementation: sse
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
error 111

Number of similar (compiler,implementation) pairs: 9, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE sse
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE sse
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE sse
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE sse
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE vec

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
bm.c: bm.c:139:30: error: always_inline function '_mm256_extract_epi64' requires target feature 'xsave', but would be inlined into function 'get_coefs' that is compiled without support for 'xsave'
bm.c: out[ (4*0 + k)*16 + i ] = (vec256_extract(buf[i], 0) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: bm.c:140:30: error: always_inline function '_mm256_extract_epi64' requires target feature 'xsave', but would be inlined into function 'get_coefs' that is compiled without support for 'xsave'
bm.c: out[ (4*1 + k)*16 + i ] = (vec256_extract(buf[i], 1) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: bm.c:141:30: error: always_inline function '_mm256_extract_epi64' requires target feature 'xsave', but would be inlined into function 'get_coefs' that is compiled without support for 'xsave'
bm.c: out[ (4*2 + k)*16 + i ] = (vec256_extract(buf[i], 2) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: bm.c:142:30: error: always_inline function '_mm256_extract_epi64' requires target feature 'xsave', but would be inlined into function 'get_coefs' that is compiled without support for 'xsave'
bm.c: out[ (4*3 + k)*16 + i ] = (vec256_extract(buf[i], 3) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: ./vec256.h:32:10: error: always_inline function '_mm256_setzero_si256' requires target feature 'xsave', but would be inlined into function 'vec256_setzero' that is compiled without support for 'xsave'
bm.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
bm.c: bm.c:139:30: error: always_inline function '_mm256_extract_epi64' requires target feature 'sse4.2', but would be inlined into function 'get_coefs' that is compiled without support for 'sse4.2'
bm.c: out[ (4*0 + k)*16 + i ] = (vec256_extract(buf[i], 0) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: bm.c:140:30: error: always_inline function '_mm256_extract_epi64' requires target feature 'sse4.2', but would be inlined into function 'get_coefs' that is compiled without support for 'sse4.2'
bm.c: out[ (4*1 + k)*16 + i ] = (vec256_extract(buf[i], 1) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: bm.c:141:30: error: always_inline function '_mm256_extract_epi64' requires target feature 'sse4.2', but would be inlined into function 'get_coefs' that is compiled without support for 'sse4.2'
bm.c: out[ (4*2 + k)*16 + i ] = (vec256_extract(buf[i], 2) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: bm.c:142:30: error: always_inline function '_mm256_extract_epi64' requires target feature 'sse4.2', but would be inlined into function 'get_coefs' that is compiled without support for 'sse4.2'
bm.c: out[ (4*3 + k)*16 + i ] = (vec256_extract(buf[i], 3) >> (k*16)) & GFMASK;
bm.c: ^
bm.c: ./vec256.h:41:41: note: expanded from macro 'vec256_extract'
bm.c: #define vec256_extract(a,i) ((uint64_t) _mm256_extract_epi64((vec256) (a),(i)))
bm.c: ^
bm.c: ./vec256.h:32:10: error: always_inline function '_mm256_setzero_si256' requires target feature 'sse4.2', but would be inlined into function 'vec256_setzero' that is compiled without support for 'sse4.2'
bm.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx T:avx

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
benes.c: In file included from transpose.h:12:0,
benes.c: from benes.c:11:
benes.c: vec256.h: In function 'vec256_set1_16b':
benes.c: vec256.h:21:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
benes.c: {
benes.c: ^
bm.c: In file included from bm.h:11:0,
bm.c: from bm.c:13:
bm.c: vec256.h: In function 'vec256_set1_16b':
bm.c: vec256.h:21:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
bm.c: {
bm.c: ^
bm.c: vec256.h: In function 'vec256_and':
bm.c: vec256.h:48:22: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
bm.c: static inline vec256 vec256_and(vec256 a, vec256 b)
bm.c: ^~~~~~~~~~
bm.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/6/include/immintrin.h:41:0,
bm.c: from vec256.h:16,
bm.c: from bm.h:11,
bm.c: from bm.c:13:
bm.c: vec256.h: In function 'vec256_set1_16b':
bm.c: /usr/lib/gcc/x86_64-linux-gnu/6/include/avxintrin.h:1300:1: error: inlining failed in call to always_inline '_mm256_set1_epi16': target specific option mismatch
bm.c: _mm256_set1_epi16 (short __A)
bm.c: ^~~~~~~~~~~~~~~~~
bm.c: In file included from bm.h:11:0,
bm.c: from bm.c:13:
bm.c: vec256.h:22:9: note: called from here
bm.c: return _mm256_set1_epi16(a);
bm.c: ^~~~~~~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 8, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE avx T:avx
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE avx T:avx
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE avx T:avx
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE avx T:avx

Compiler output

Implementation: sse
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
decrypt.c: In file included from decrypt.c:8:
decrypt.c: In file included from ./fft_tr.h:10:
decrypt.c: ./vec128.h:40:9: error: always_inline function '_mm_testz_si128' requires target feature 'ssse3', but would be inlined into function 'vec128_testz' that is compiled without support for 'ssse3'
decrypt.c: return _mm_testz_si128(a, a);
decrypt.c: ^
decrypt.c: fatal error: error in backend: Cannot select: 0x558219f133a0: i32 = X86ISD::PTEST 0x558219f12000, 0x558219f12000
decrypt.c: 0x558219f12000: v2i64,ch = CopyFromReg 0x558219dccb60, Register:v2i64 %vreg81
decrypt.c: 0x558219ecf0e0: v2i64 = Register %vreg81
decrypt.c: 0x558219f12000: v2i64,ch = CopyFromReg 0x558219dccb60, Register:v2i64 %vreg81
decrypt.c: 0x558219ecf0e0: v2i64 = Register %vreg81
decrypt.c: In function: crypto_kem_mceliece460896_sse_constbranchindex_decrypt
decrypt.c: clang: error: clang frontend command failed with exit code 70 (use -v to see invocation)
decrypt.c: clang version 3.8.1-24 (tags/RELEASE_381/final)
decrypt.c: Target: x86_64-pc-linux-gnu
decrypt.c: Thread model: posix
decrypt.c: InstalledDir: /usr/bin
decrypt.c: clang: note: diagnostic msg: PLEASE submit a bug report to http://llvm.org/bugs/ and include the crash backtrace, preprocessed source, and associated run script.
decrypt.c: clang: note: diagnostic msg:
decrypt.c: ********************
decrypt.c:
decrypt.c: PLEASE ATTACH THE FOLLOWING FILES TO THE BUG REPORT:
decrypt.c: Preprocessed source(s) and associated run script(s) are located at:
decrypt.c: clang: note: diagnostic msg: /tmp/decrypt-b294dd.c
decrypt.c: clang: note: diagnostic msg: /tmp/decrypt-b294dd.sh
decrypt.c: clang: note: diagnostic msg:
decrypt.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE sse