Implementation notes: amd64, latour, crypto_sort/int32

Computer: latour
Architecture: amd64
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20201130
Operation: crypto_sort
Primitive: int32

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
25929	1843 0 0	11326 784 736	`T:radix256sml`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
27648	1341 0 0	13732 736 808	`T:radix256ml`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
28746	1373 0 0	11539 728 808	`T:radix256ml`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
29340	3171 0 0	14728 792 736	`T:radix256sml`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
29457	2006 0 0	13416 792 736	`T:radix256ml`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
29952	1179 0 0	10231 712 776	`T:radix256ml`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
30114	3171 0 0	14600 792 736	`T:radix256sml`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
30600	3171 0 0	13792 792 736	`T:radix256sml`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
31167	1941 0 0	14348 736 808	`T:radix256sml`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
31437	2006 0 0	12608 792 736	`T:radix256ml`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
31626	2053 0 0	12235 728 808	`T:radix256sml`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
31680	1937 0 0	11955 728 808	`T:radix256sml`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
31770	1292 0 0	11299 728 808	`T:radix256ml`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
33210	2006 0 0	13544 792 736	`T:radix256ml`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
33750	3171 0 0	13792 792 736	`T:radix256sml`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
35505	2006 0 0	12608 792 736	`T:radix256ml`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
36603	1182 0 0	10638 784 736	`T:radix256ml`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
37323	1774 0 0	10839 712 776	`T:radix256sml`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
58671	606 0 0	12972 736 808	`T:herf`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
60210	556 0 0	9599 712 776	`T:herf`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
60246	612 0 0	10747 728 808	`T:herf`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
76014	928 0 0	12432 792 736	`T:herf`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
76905	928 0 0	12304 792 736	`T:herf`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
77877	510 0 0	9950 784 736	`T:herf`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
80028	928 0 0	11496 792 736	`T:herf`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
81648	1304 0 0	11541 736 800	`T:stdsort`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
82035	1348 0 0	12071 832 728	`T:stdsort`	`clang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
82305	1115 0 0	10701 824 728	`T:stdsort`	`clang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
82440	1348 0 0	12071 832 728	`T:stdsort`	`clang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
83124	618 0 0	10603 728 808	`T:herf`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
83466	1996 0 0	13679 832 728	`T:stdsort`	`clang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
84888	928 0 0	11496 792 736	`T:herf`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
84951	1345 0 0	13806 744 800	`T:stdsort`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
89613	1300 0 0	11389 736 800	`T:stdsort`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
89784	964 0 0	10113 720 768	`T:stdsort`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
91854	8559 0 0	18547 728 808	`x863`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
92466	8718 0 0	21076 736 808	`x863`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
93051	8302 0 0	18435 728 808	`x863`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
94554	5089 0 0	16496 792 736	`x863`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
94752	5089 0 0	16624 792 736	`x863`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
96138	4902 0 0	15496 792 736	`x863`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
96183	4902 0 0	15496 792 736	`x863`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
96219	4157 0 0	13614 784 736	`x863`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
106497	1569 0 0	13080 792 736	`x86`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
106623	1569 0 0	12952 792 736	`x86`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
108270	1361 0 0	11936 792 736	`x86`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
108360	1361 0 0	11936 792 736	`x86`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
109953	1192 0 0	11331 728 808	`x86`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
110016	1160 0 0	10598 784 736	`x86`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
112167	1192 0 0	13556 736 808	`x86`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
112905	1043 0 0	10087 712 776	`x86`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
122499	1298 0 0	11283 728 808	`x86`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
129474	4178 0 0	13263 712 776	`x863`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
159381	1302 0 0	11872 792 736	`portable4`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
159642	1302 0 0	11872 792 736	`portable4`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
160677	2067 0 0	14436 736 808	`portable4`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
162108	1414 0 0	12920 792 736	`portable4`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
162171	1414 0 0	12792 792 736	`portable4`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
164574	716 0 0	10150 784 736	`portable4`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
165528	799 0 0	10931 728 808	`portable4`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
166662	868 0 0	10851 728 808	`portable4`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
171351	1273 0 0	10311 712 776	`portable5`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
173691	687 0 0	9727 712 776	`portable4`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
178038	1376 0 0	10806 784 736	`portable5`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
178119	2278 0 0	13656 792 736	`portable5`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
178452	2278 0 0	13784 792 736	`portable5`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
181017	2054 0 0	12624 792 736	`portable5`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
181053	2054 0 0	12624 792 736	`portable5`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
186408	1449 0 0	11587 728 808	`portable5`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
187308	2712 0 0	15076 736 808	`portable5`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
189504	1563 0 0	11539 728 808	`portable5`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
195975	391 0 0	10960 792 736	`portable3`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
195984	391 0 0	10960 792 736	`portable3`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
197109	375 0 0	11752 792 736	`portable3`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
199746	375 0 0	11880 792 736	`portable3`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
201141	450 0 0	10427 728 808	`portable3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
204552	425 0 0	10571 728 808	`portable3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
204741	425 0 0	12796 736 808	`portable3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826
215460	337 0 0	9766 784 736	`portable3`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200829	20200826
222552	350 0 0	9399 712 776	`portable3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200829	20200826

Test failure

Implementation: T:krasnov
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

error 111

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:krasnov
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:krasnov
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:krasnov
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:krasnov

Compiler output

Implementation: T:aspas
Security model: timingleaks
Compiler: clang++ -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

api.cpp: In file included from api.cpp:3:
api.cpp: In file included from ./aspas.h:30:
api.cpp: In file included from /usr/bin/../lib/gcc/x86_64-linux-gnu/5.4.0/../../../../include/c++/5.4.0/cstdint:35:
api.cpp: /usr/bin/../lib/gcc/x86_64-linux-gnu/5.4.0/../../../../include/c++/5.4.0/bits/c++0x_warning.h:32:2: error: This file requires compiler and library support for the ISO C++ 2011 standard. This support must be enabled with the -std=c++11 or -std=gnu++11 compiler options.
api.cpp: #error This file requires compiler and library support \
api.cpp: ^
api.cpp: In file included from api.cpp:3:
api.cpp: ./aspas.h:49:6: warning: scoped enumerations are a C++11 extension [-Wc++11-extensions]
api.cpp: enum class simd_width : std::int8_t
api.cpp: ^
api.cpp: ./aspas.h:49:12: error: ISO C++ forbids forward references to 'enum' types
api.cpp: enum class simd_width : std::int8_t
api.cpp: ^
api.cpp: ./aspas.h:49:23: error: expected unqualified-id
api.cpp: enum class simd_width : std::int8_t
api.cpp: ^
api.cpp: ./aspas.h:121:15: error: no type named 'enable_if' in namespace 'std'
api.cpp: typename std::enable_if<std::is_same<T, int>::value>::type
api.cpp: ~~~~~~~~~~~~~~^~~~~~~~~
api.cpp: ./aspas.h:121:24: error: expected unqualified-id
api.cpp: typename std::enable_if<std::is_same<T, int>::value>::type
api.cpp: ^
api.cpp: ./aspas.h:138:15: error: no type named 'enable_if' in namespace 'std'
api.cpp: typename std::enable_if<std::is_same<T, float>::value>::type
api.cpp: ~~~~~~~~~~~~~~^~~~~~~~~
api.cpp: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang++ -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:aspas
clang++ -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:aspas
clang++ -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:aspas
clang++ -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:aspas

Compiler output

Implementation: T:aspas
Security model: timingleaks
Compiler: g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

api.cpp: In file included from /usr/include/c++/5/cstdint:35:0,
api.cpp: from aspas.h:30,
api.cpp: from api.cpp:3:
api.cpp: /usr/include/c++/5/bits/c++0x_warning.h:32:2: error: #error This file requires compiler and library support for the ISO C++ 2011 standard. This support must be enabled with the -std=c++11 or -std=gnu++11 compiler options.
api.cpp: #error This file requires compiler and library support \
api.cpp: ^
api.cpp: In file included from api.cpp:3:0:
api.cpp: aspas.h:49:1: warning: scoped enums only available with -std=c++11 or -std=gnu++11
api.cpp: enum class simd_width : std::int8_t
api.cpp: ^
api.cpp: aspas.h:49:1: warning: elaborated-type-specifier for a scoped enum must not use the 'class' keyword
api.cpp: aspas.h:49:12: error: use of enum 'simd_width' without previous declaration
api.cpp: enum class simd_width : std::int8_t
api.cpp: ^
api.cpp: aspas.h:49:23: error: expected unqualified-id before ':' token
api.cpp: enum class simd_width : std::int8_t
api.cpp: ^
api.cpp: aspas.h:121:15: error: 'enable_if' in namespace 'std' does not name a template type
api.cpp: typename std::enable_if<std::is_same<T, int>::value>::type
api.cpp: ^
api.cpp: aspas.h:121:24: error: expected unqualified-id before '<' token
api.cpp: typename std::enable_if<std::is_same<T, int>::value>::type
api.cpp: ^
api.cpp: aspas.h:138:15: error: 'enable_if' in namespace 'std' does not name a template type
api.cpp: typename std::enable_if<std::is_same<T, float>::value>::type
api.cpp: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:aspas
g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:aspas
g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:aspas
g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:aspas

Compiler output

Implementation: avx2
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

sort.c: sort.c:940:40: error: always_inline function '_mm256_set1_epi32' requires target feature 'xsave', but would be inlined into function 'int32_sort' that is compiled without support for 'xsave'
sort.c: for (i = q>>3;i < q>>2;++i) y[i] = _mm256_set1_epi32(0x7fffffff);
sort.c: ^
sort.c: sort.c:956:22: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'int32_sort' that is compiled without support for 'xsave'
sort.c: int32x8 x0 = int32x8_load(&x[i]);
sort.c: ^
sort.c: sort.c:9:25: note: expanded from macro 'int32x8_load'
sort.c: #define int32x8_load(z) _mm256_loadu_si256((__m256i *) (z))
sort.c: ^
sort.c: sort.c:957:22: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'int32_sort' that is compiled without support for 'xsave'
sort.c: int32x8 x1 = int32x8_load(&x[i+q]);
sort.c: ^
sort.c: sort.c:9:25: note: expanded from macro 'int32x8_load'
sort.c: #define int32x8_load(z) _mm256_loadu_si256((__m256i *) (z))
sort.c: ^
sort.c: sort.c:958:22: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'int32_sort' that is compiled without support for 'xsave'
sort.c: int32x8 x2 = int32x8_load(&x[i+2*q]);
sort.c: ^
sort.c: sort.c:9:25: note: expanded from macro 'int32x8_load'
sort.c: #define int32x8_load(z) _mm256_loadu_si256((__m256i *) (z))
sort.c: ^
sort.c: sort.c:959:22: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'int32_sort' that is compiled without support for 'xsave'
sort.c: int32x8 x3 = int32x8_load(&x[i+3*q]);
sort.c: ^
sort.c: sort.c:9:25: note: expanded from macro 'int32x8_load'
sort.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2

Compiler output

Implementation: avx2
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

sort.c: sort.c:940:40: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'int32_sort' that is compiled without support for 'sse4.2'
sort.c: for (i = q>>3;i < q>>2;++i) y[i] = _mm256_set1_epi32(0x7fffffff);
sort.c: ^
sort.c: sort.c:956:22: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'int32_sort' that is compiled without support for 'sse4.2'
sort.c: int32x8 x0 = int32x8_load(&x[i]);
sort.c: ^
sort.c: sort.c:9:25: note: expanded from macro 'int32x8_load'
sort.c: #define int32x8_load(z) _mm256_loadu_si256((__m256i *) (z))
sort.c: ^
sort.c: sort.c:957:22: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'int32_sort' that is compiled without support for 'sse4.2'
sort.c: int32x8 x1 = int32x8_load(&x[i+q]);
sort.c: ^
sort.c: sort.c:9:25: note: expanded from macro 'int32x8_load'
sort.c: #define int32x8_load(z) _mm256_loadu_si256((__m256i *) (z))
sort.c: ^
sort.c: sort.c:958:22: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'int32_sort' that is compiled without support for 'sse4.2'
sort.c: int32x8 x2 = int32x8_load(&x[i+2*q]);
sort.c: ^
sort.c: sort.c:9:25: note: expanded from macro 'int32x8_load'
sort.c: #define int32x8_load(z) _mm256_loadu_si256((__m256i *) (z))
sort.c: ^
sort.c: sort.c:959:22: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'int32_sort' that is compiled without support for 'sse4.2'
sort.c: int32x8 x3 = int32x8_load(&x[i+3*q]);
sort.c: ^
sort.c: sort.c:9:25: note: expanded from macro 'int32x8_load'
sort.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2

Compiler output

Implementation: avx2
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

sort.c: sort.c: In function 'int32_sort':
sort.c: sort.c:940:38: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
sort.c: for (i = q>>3;i < q>>2;++i) y[i] = _mm256_set1_epi32(0x7fffffff);
sort.c: ^
sort.c: sort.c: In function 'merge16_finish':
sort.c: sort.c:55:13: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
sort.c: static void merge16_finish(int32 *x,int32x8 x0,int32x8 x1,int flagdown)
sort.c: ^
sort.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
sort.c: from sort.c:4:
sort.c: sort.c: In function 'minmax_vector':
sort.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:900:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
sort.c: _mm256_storeu_si256 (__m256i *__P, __m256i __A)
sort.c: ^
sort.c: sort.c:10:28: error: called from here
sort.c: #define int32x8_store(z,i) _mm256_storeu_si256((__m256i *) (z),(i))
sort.c: ^
sort.c: sort.c:38:5: note: in expansion of macro 'int32x8_store'
sort.c: int32x8_store(y + n - 8,y0);
sort.c: ^
sort.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
sort.c: from sort.c:4:
sort.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:900:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
sort.c: _mm256_storeu_si256 (__m256i *__P, __m256i __A)
sort.c: ^
sort.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2

Compiler output

Implementation: T:herf
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

sort.c: sort.c:133:17: warning: passing 'int32 [n]' to parameter of type 'uint32 *' (aka 'unsigned int *') converts between pointers to integer types with different sign [-Wpointer-sign]
sort.c: RadixSort11(x,y,n);
sort.c: ^
sort.c: sort.c:47:48: note: passing argument to parameter 'sort' here
sort.c: static void RadixSort11(uint32 *array, uint32 *sort, uint32 elements)
sort.c: ^
sort.c: 1 warning generated.

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:herf
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:herf
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:herf
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:herf
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:herf

Compiler output

Implementation: T:krasnov
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

qsort_AVX2_HSW_256bit_int.S: qsort_AVX2_HSW_256bit_int.S:3:16: error: unknown token in expression
qsort_AVX2_HSW_256bit_int.S: .set pivotALU, %ecx
qsort_AVX2_HSW_256bit_int.S: ^
qsort_AVX2_HSW_256bit_int.S: qsort_AVX2_HSW_256bit_int.S:3:16: error: missing expression
qsort_AVX2_HSW_256bit_int.S: .set pivotALU, %ecx
qsort_AVX2_HSW_256bit_int.S: ^
qsort_AVX2_HSW_256bit_int.S: qsort_AVX2_HSW_256bit_int.S:5:10: error: unknown token in expression
qsort_AVX2_HSW_256bit_int.S: .set A0, %ymm0
qsort_AVX2_HSW_256bit_int.S: ^
qsort_AVX2_HSW_256bit_int.S: qsort_AVX2_HSW_256bit_int.S:5:10: error: missing expression
qsort_AVX2_HSW_256bit_int.S: .set A0, %ymm0
qsort_AVX2_HSW_256bit_int.S: ^
qsort_AVX2_HSW_256bit_int.S: qsort_AVX2_HSW_256bit_int.S:7:10: error: unknown token in expression
qsort_AVX2_HSW_256bit_int.S: .set A2, %ymm2
qsort_AVX2_HSW_256bit_int.S: ^
qsort_AVX2_HSW_256bit_int.S: qsort_AVX2_HSW_256bit_int.S:7:10: error: missing expression
qsort_AVX2_HSW_256bit_int.S: .set A2, %ymm2
qsort_AVX2_HSW_256bit_int.S: ^
qsort_AVX2_HSW_256bit_int.S: qsort_AVX2_HSW_256bit_int.S:9:10: error: unknown token in expression
qsort_AVX2_HSW_256bit_int.S: .set A4, %ymm4
qsort_AVX2_HSW_256bit_int.S: ^
qsort_AVX2_HSW_256bit_int.S: qsort_AVX2_HSW_256bit_int.S:9:10: error: missing expression
qsort_AVX2_HSW_256bit_int.S: .set A4, %ymm4
qsort_AVX2_HSW_256bit_int.S: ^
qsort_AVX2_HSW_256bit_int.S: qsort_AVX2_HSW_256bit_int.S:11:10: error: unknown token in expression
qsort_AVX2_HSW_256bit_int.S: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:krasnov
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:krasnov
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:krasnov
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:krasnov
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:krasnov

Compiler output

Implementation: oldavx2
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

int32_sort.c: int32_sort.c:330:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'minmax8' that is compiled without support for 'xsave'
int32_sort.c: __m256i a = _mm256_loadu_si256((__m256i *) x);
int32_sort.c: ^
int32_sort.c: int32_sort.c:331:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'minmax8' that is compiled without support for 'xsave'
int32_sort.c: __m256i b = _mm256_loadu_si256((__m256i *) y);
int32_sort.c: ^
int32_sort.c: int32_sort.c:332:3: error: always_inline function '_mm256_storeu_si256' requires target feature 'xsave', but would be inlined into function 'minmax8' that is compiled without support for 'xsave'
int32_sort.c: _mm256_storeu_si256((__m256i *) x,_mm256_min_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:332:37: error: always_inline function '_mm256_min_epi32' requires target feature 'xsave', but would be inlined into function 'minmax8' that is compiled without support for 'xsave'
int32_sort.c: _mm256_storeu_si256((__m256i *) x,_mm256_min_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:333:3: error: always_inline function '_mm256_storeu_si256' requires target feature 'xsave', but would be inlined into function 'minmax8' that is compiled without support for 'xsave'
int32_sort.c: _mm256_storeu_si256((__m256i *) y,_mm256_max_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:333:37: error: always_inline function '_mm256_max_epi32' requires target feature 'xsave', but would be inlined into function 'minmax8' that is compiled without support for 'xsave'
int32_sort.c: _mm256_storeu_si256((__m256i *) y,_mm256_max_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:364:34: error: always_inline function '_mm_min_epi32' requires target feature 'sse4.1', but would be inlined into function 'minmax4' that is compiled without support for 'sse4.1'
int32_sort.c: _mm_storeu_si128((__m128i *) x,_mm_min_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:365:34: error: always_inline function '_mm_max_epi32' requires target feature 'sse4.1', but would be inlined into function 'minmax4' that is compiled without support for 'sse4.1'
int32_sort.c: _mm_storeu_si128((__m128i *) y,_mm_max_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:16:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'minmax02through1315' that is compiled without support for 'xsave'
int32_sort.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	oldavx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	oldavx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	oldavx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	oldavx2

Compiler output

Implementation: oldavx2
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

int32_sort.c: int32_sort.c:330:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'minmax8' that is compiled without support for 'sse4.2'
int32_sort.c: __m256i a = _mm256_loadu_si256((__m256i *) x);
int32_sort.c: ^
int32_sort.c: int32_sort.c:331:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'minmax8' that is compiled without support for 'sse4.2'
int32_sort.c: __m256i b = _mm256_loadu_si256((__m256i *) y);
int32_sort.c: ^
int32_sort.c: int32_sort.c:332:3: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'minmax8' that is compiled without support for 'sse4.2'
int32_sort.c: _mm256_storeu_si256((__m256i *) x,_mm256_min_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:332:37: error: always_inline function '_mm256_min_epi32' requires target feature 'sse4.2', but would be inlined into function 'minmax8' that is compiled without support for 'sse4.2'
int32_sort.c: _mm256_storeu_si256((__m256i *) x,_mm256_min_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:333:3: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'minmax8' that is compiled without support for 'sse4.2'
int32_sort.c: _mm256_storeu_si256((__m256i *) y,_mm256_max_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:333:37: error: always_inline function '_mm256_max_epi32' requires target feature 'sse4.2', but would be inlined into function 'minmax8' that is compiled without support for 'sse4.2'
int32_sort.c: _mm256_storeu_si256((__m256i *) y,_mm256_max_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:364:34: error: always_inline function '_mm_min_epi32' requires target feature 'ssse3', but would be inlined into function 'minmax4' that is compiled without support for 'ssse3'
int32_sort.c: _mm_storeu_si128((__m128i *) x,_mm_min_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:365:34: error: always_inline function '_mm_max_epi32' requires target feature 'ssse3', but would be inlined into function 'minmax4' that is compiled without support for 'ssse3'
int32_sort.c: _mm_storeu_si128((__m128i *) y,_mm_max_epi32(a,b));
int32_sort.c: ^
int32_sort.c: int32_sort.c:16:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'minmax02through1315' that is compiled without support for 'sse4.2'
int32_sort.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	oldavx2

Compiler output

Implementation: oldavx2
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

int32_sort.c: int32_sort.c: In function 'minmax8':
int32_sort.c: int32_sort.c:330:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
int32_sort.c: __m256i a = _mm256_loadu_si256((__m256i *) x);
int32_sort.c: ^
int32_sort.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
int32_sort.c: from int32_sort.c:3:
int32_sort.c: int32_sort.c: In function 'minmax02through1315':
int32_sort.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:900:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
int32_sort.c: _mm256_storeu_si256 (__m256i *__P, __m256i __A)
int32_sort.c: ^
int32_sort.c: int32_sort.c:25:3: error: called from here
int32_sort.c: _mm256_storeu_si256((__m256i *) (x + 8),b);
int32_sort.c: ^
int32_sort.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
int32_sort.c: from int32_sort.c:3:
int32_sort.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:900:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
int32_sort.c: _mm256_storeu_si256 (__m256i *__P, __m256i __A)
int32_sort.c: ^
int32_sort.c: int32_sort.c:24:3: error: called from here
int32_sort.c: _mm256_storeu_si256((__m256i *) x,a);
int32_sort.c: ^
int32_sort.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
int32_sort.c: from int32_sort.c:3:
int32_sort.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:878:1: error: inlining failed in call to always_inline '_mm256_unpackhi_epi64': target specific option mismatch
int32_sort.c: _mm256_unpackhi_epi64 (__m256i __A, __m256i __B)
int32_sort.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	oldavx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	oldavx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	oldavx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	oldavx2

Compiler output

Implementation: T:sid1607
Security model: timingleaks
Compiler: clang++ -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

merge_sort.cpp: merge_sort.cpp:30:3: warning: 'auto' type specifier is a C++11 extension [-Wc++11-extensions]
merge_sort.cpp: auto t = a;
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:128:3: warning: 'auto' type specifier is a C++11 extension [-Wc++11-extensions]
merge_sort.cpp: auto a8_1 = register_shuffle(a8, global_masks.swap_128);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:129:3: warning: 'auto' type specifier is a C++11 extension [-Wc++11-extensions]
merge_sort.cpp: auto b8_1 = register_shuffle(b8, global_masks.swap_128);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:134:3: warning: 'auto' type specifier is a C++11 extension [-Wc++11-extensions]
merge_sort.cpp: auto a4 = _mm256_blend_epi32(mina, maxa, 0xf0);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:135:3: warning: 'auto' type specifier is a C++11 extension [-Wc++11-extensions]
merge_sort.cpp: auto b4 = _mm256_blend_epi32(minb, maxb, 0xf0);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:138:3: warning: 'auto' type specifier is a C++11 extension [-Wc++11-extensions]
merge_sort.cpp: auto a4_1 = _mm256_shuffle_epi32(a4, 0x4e);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:139:3: warning: 'auto' type specifier is a C++11 extension [-Wc++11-extensions]
merge_sort.cpp: auto b4_1 = _mm256_shuffle_epi32(b4, 0x4e);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:144:3: warning: 'auto' type specifier is a C++11 extension [-Wc++11-extensions]
merge_sort.cpp: auto a2 = _mm256_unpacklo_epi64(mina, maxa);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:145:3: warning: 'auto' type specifier is a C++11 extension [-Wc++11-extensions]
merge_sort.cpp: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang++ -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sid1607
clang++ -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sid1607
clang++ -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sid1607
clang++ -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sid1607

Compiler output

Implementation: T:sid1607
Security model: timingleaks
Compiler: g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

api.cpp: In file included from api.cpp:3:0:
api.cpp: merge_sort.h: In function '__m256i load_reg256(int*)':
api.cpp: merge_sort.h:17:34: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
api.cpp: inline __m256i load_reg256(int *a) {
api.cpp: ^
merge_sort.cpp: In file included from merge_sort.cpp:1:0:
merge_sort.cpp: merge_sort.h: In function '__m256i load_reg256(int*)':
merge_sort.cpp: merge_sort.h:17:34: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
merge_sort.cpp: inline __m256i load_reg256(int *a) {
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp: In function 'void minmax(__m256i&, __m256i&)':
merge_sort.cpp: merge_sort.cpp:30:8: error: 't' does not name a type
merge_sort.cpp: auto t = a;
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:32:24: error: 't' was not declared in this scope
merge_sort.cpp: b = _mm256_max_epi32(t, b);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp: In function 'void intra_register_sort(__m256i&, __m256i&)':
merge_sort.cpp: merge_sort.cpp:128:8: error: 'a8_1' does not name a type
merge_sort.cpp: auto a8_1 = register_shuffle(a8, global_masks.swap_128);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:129:8: error: 'b8_1' does not name a type
merge_sort.cpp: auto b8_1 = register_shuffle(b8, global_masks.swap_128);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:131:14: error: 'a8_1' was not declared in this scope
merge_sort.cpp: minmax(a8, a8_1, mina, maxa);
merge_sort.cpp: ^
merge_sort.cpp: merge_sort.cpp:132:14: error: 'b8_1' was not declared in this scope
merge_sort.cpp: minmax(b8, b8_1, minb, maxb);
merge_sort.cpp: ^
merge_sort.cpp: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sid1607
g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sid1607
g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sid1607
g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sid1607