Implementation notes: aarch64, gcc185, crypto_stream/chacha12

Computer: gcc185
Microarchitecture: aarch64; Skylark (503f0002)
Architecture: aarch64
CPU ID: 503f0002
SUPERCOP version: 20240107
Operation: crypto_stream
Primitive: chacha12

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
7875	2412 0 4	15629 824 808	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
7875	3372 0 4	17814 832 824	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
8550	2044 0 4	14285 808 800	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
8625	3020 0 4	17478 832 824	`dolbeau/mipsel-msa`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
8625	3044 0 4	17486 832 824	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
8700	3044 0 4	17486 832 824	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
9000	3272 0 1	15804 792 808	`dolbeau/arm-neon`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9075	3780 0 1	18178 800 808	`dolbeau/arm-neon`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9075	4104 0 1	20058 800 816	`dolbeau/arm-neon`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9075	4104 0 1	20058 800 816	`dolbeau/arm-neon`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9150	3148 0 1	15834 800 808	`dolbeau/arm-neon`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9150	2840 0 1	17226 800 808	`e/merged`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9150	2856 0 1	18786 800 816	`e/merged`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9150	2520 0 1	15210 800 808	`e/merged`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9150	2856 0 1	18786 800 816	`e/merged`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9225	3964 0 4	17189 824 808	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
9225	4812 0 4	19246 832 824	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
9225	2720 0 1	18642 800 816	`e/regs`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9225	2720 0 1	18642 800 816	`e/regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9750	3328 0 4	15565 808 800	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
9825	2708 0 1	17082 800 808	`e/regs`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9900	2728 0 1	18666 800 816	`dolbeau/mipsel-msa`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9900	2728 0 1	18666 800 816	`dolbeau/mipsel-msa`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9900	2728 0 1	18658 800 816	`e/ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9900	2728 0 1	18658 800 816	`e/ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
10125	2524 0 1	15036 792 808	`e/merged`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
10275	2404 0 1	16786 800 808	`dolbeau/mipsel-msa`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
10275	2404 0 1	16778 800 808	`e/ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
11250	4308 0 4	17477 824 808	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
11925	2188 0 4	15413 824 808	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
12150	2332 0 1	15018 800 808	`e/regs`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
12450	11054 1104 0	1198452 145673 15128	`T:cryptopp`	`clang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
12525	11154 1104 0	1200100 145673 15144	`T:cryptopp`	`clang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
12525	18115 3360 0	1202732 147873 15128	`T:cryptopp`	`clang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
12525	6865 976 0	1192216 145649 15128	`T:cryptopp`	`clang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
12525	17919 2368 0	1200813 146929 15144	`T:cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
12600	16879 2368 0	1199480 146937 15144	`T:cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
12675	7411 2880 0	1190784 147577 15128	`T:cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
13050	18242 2368 0	1202355 146929 15144	`T:cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
13125	2360 0 1	14876 792 808	`e/regs`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
13725	3720 0 4	16885 824 808	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
14175	1784 0 1	14474 800 808	`dolbeau/mipsel-msa`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
14175	1784 0 1	14466 800 808	`e/ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
14400	1816 0 4	14061 808 800	`dolbeau/mipsel-msa`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
14400	1816 0 4	14053 808 800	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
14700	2204 0 4	15429 824 808	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
14850	2236 0 4	15477 824 808	`dolbeau/mipsel-msa`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
16200	1916 0 1	14420 792 808	`dolbeau/mipsel-msa`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
16200	1916 0 1	14412 792 808	`e/ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
16950	2596 0 4	15781 824 808	`dolbeau/mipsel-msa`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
16950	2596 0 4	15765 824 808	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
18975	1976 0 4	14197 808 800	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
33525	3092 0 4	16261 824 808	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212

Compiler output

Implementation: amd64-ssse3
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

chacha.S: chacha.S:19:5: error: unknown token in expression
chacha.S: mov %rsp,%r11
chacha.S: ^
chacha.S: chacha.S:19:5: error: invalid operand
chacha.S: mov %rsp,%r11
chacha.S: ^
chacha.S: chacha.S:20:9: error: unknown token in expression
chacha.S: and $31,%r11
chacha.S: ^
chacha.S: chacha.S:20:9: error: invalid operand
chacha.S: and $31,%r11
chacha.S: ^
chacha.S: chacha.S:21:10: error: unknown token in expression
chacha.S: add $384,%r11
chacha.S: ^
chacha.S: chacha.S:21:10: error: invalid operand
chacha.S: add $384,%r11
chacha.S: ^
chacha.S: chacha.S:22:5: error: unknown token in expression
chacha.S: sub %r11,%rsp
chacha.S: ^
chacha.S: chacha.S:22:5: error: invalid operand
chacha.S: sub %r11,%rsp
chacha.S: ^
chacha.S: chacha.S:23:5: error: unknown token in expression
chacha.S: ...

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3

Compiler output

Implementation: amd64-ssse3
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

chacha.S: chacha.S: Assembler messages:
chacha.S: chacha.S:19: Error: operand 1 must be an integer register -- `mov %rsp,%r11'
chacha.S: chacha.S:20: Error: operand 1 must be an integer or stack pointer register -- `and $31,%r11'
chacha.S: chacha.S:21: Error: operand 1 must be an integer or stack pointer register -- `add $384,%r11'
chacha.S: chacha.S:22: Error: operand 1 must be an integer or stack pointer register -- `sub %r11,%rsp'
chacha.S: chacha.S:23: Error: operand 1 must be an integer register -- `mov %rdi,%r8'
chacha.S: chacha.S:24: Error: operand 1 must be an integer register -- `mov %rsi,%rsi'
chacha.S: chacha.S:25: Error: operand 1 must be an integer register -- `mov %rsi,%rdi'
chacha.S: chacha.S:26: Error: operand 1 must be an integer register -- `mov %rdx,%rdx'
chacha.S: chacha.S:27: Error: operand 1 must be an integer or stack pointer register -- `cmp $0,%rdx'
chacha.S: chacha.S:29: Error: unknown mnemonic `jbe' -- `jbe ._done'
chacha.S: chacha.S:31: Error: operand 1 must be an integer register -- `mov $0,%rax'
chacha.S: chacha.S:33: Error: operand 1 must be an integer register -- `mov %rdx,%rcx'
chacha.S: chacha.S:35: Error: unknown mnemonic `rep' -- `rep stosb'
chacha.S: chacha.S:37: Error: operand 1 must be an integer or stack pointer register -- `sub %rdx,%rdi'
chacha.S: chacha.S:39: Error: unknown mnemonic `jmp' -- `jmp ._start'
chacha.S: chacha.S:47: Error: operand 1 must be an integer register -- `mov %rsp,%r11'
chacha.S: chacha.S:48: Error: operand 1 must be an integer or stack pointer register -- `and $31,%r11'
chacha.S: chacha.S:49: Error: operand 1 must be an integer or stack pointer register -- `add $384,%r11'
chacha.S: chacha.S:50: Error: operand 1 must be an integer or stack pointer register -- `sub %r11,%rsp'
chacha.S: chacha.S:52: Error: operand 1 must be an integer register -- `mov %rdi,%r8'
chacha.S: chacha.S:54: Error: operand 1 must be an integer register -- `mov %rsi,%rsi'
chacha.S: chacha.S:56: Error: operand 1 must be an integer register -- `mov %rdx,%rdi'
chacha.S: chacha.S:58: Error: operand 1 must be an integer register -- `mov %rcx,%rdx'
chacha.S: chacha.S:60: Error: operand 1 must be an integer or stack pointer register -- `cmp $0,%rdx'
chacha.S: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64-ssse3
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64-ssse3
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64-ssse3
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64-ssse3

Compiler output

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

stream.c: In file included from stream.c:11:
stream.c: /usr/bin/../lib/clang/17/include/immintrin.h:14:2: error: "This header is only meant to be used on x86 and x64 architecture"
stream.c: 14 | #error "This header is only meant to be used on x86 and x64 architecture"
stream.c: | ^
stream.c: In file included from stream.c:11:
stream.c: In file included from /usr/bin/../lib/clang/17/include/immintrin.h:17:
stream.c: In file included from /usr/bin/../lib/clang/17/include/x86gprintrin.h:15:
stream.c: /usr/bin/../lib/clang/17/include/hresetintrin.h:42:27: error: invalid input constraint 'a' in asm
stream.c: 42 | __asm__ ("hreset $0" :: "a"(__eax));
stream.c: | ^
stream.c: In file included from stream.c:11:
stream.c: In file included from /usr/bin/../lib/clang/17/include/immintrin.h:21:
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:14:2: error: "This header is only meant to be used on x86 and x64 architecture"
stream.c: 14 | #error "This header is only meant to be used on x86 and x64 architecture"
stream.c: | ^
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:54:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
stream.c: 54 | return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
stream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:133:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
stream.c: 133 | return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
stream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:163:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
stream.c: 163 | return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
stream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:193:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
stream.c: ...

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

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

Compiler output

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

stream.c: stream.c:11:10: fatal error: immintrin.h: No such file or directory
stream.c: #include <immintrin.h>
stream.c: ^~~~~~~~~~~~~
stream.c: compilation terminated.

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

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

Compiler output

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

stream.c: In file included from stream.c:8:
stream.c: /usr/bin/../lib/clang/17/include/immintrin.h:14:2: error: "This header is only meant to be used on x86 and x64 architecture"
stream.c: 14 | #error "This header is only meant to be used on x86 and x64 architecture"
stream.c: | ^
stream.c: In file included from stream.c:8:
stream.c: In file included from /usr/bin/../lib/clang/17/include/immintrin.h:17:
stream.c: In file included from /usr/bin/../lib/clang/17/include/x86gprintrin.h:15:
stream.c: /usr/bin/../lib/clang/17/include/hresetintrin.h:42:27: error: invalid input constraint 'a' in asm
stream.c: 42 | __asm__ ("hreset $0" :: "a"(__eax));
stream.c: | ^
stream.c: In file included from stream.c:8:
stream.c: In file included from /usr/bin/../lib/clang/17/include/immintrin.h:21:
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:14:2: error: "This header is only meant to be used on x86 and x64 architecture"
stream.c: 14 | #error "This header is only meant to be used on x86 and x64 architecture"
stream.c: | ^
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:54:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
stream.c: 54 | return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
stream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:133:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
stream.c: 133 | return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
stream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:163:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
stream.c: 163 | return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
stream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: /usr/bin/../lib/clang/17/include/mmintrin.h:193:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
stream.c: ...

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

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

Compiler output

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

stream.c: stream.c:8:10: fatal error: immintrin.h: No such file or directory
stream.c: #include <immintrin.h>
stream.c: ^~~~~~~~~~~~~
stream.c: compilation terminated.

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

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

Compiler output

Implementation: krovetz/vec128
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

stream.c: stream.c:80:2: error: -- Implementation supports only machines with neon, altivec or SSE2
stream.c: 80 | #error -- Implementation supports only machines with neon, altivec or SSE2
stream.c: | ^
stream.c: stream.c:151:14: error: call to undeclared function 'NONCE'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
stream.c: 151 | vec s3 = NONCE(np);
stream.c: | ^
stream.c: stream.c:151:9: error: initializing 'vec' (vector of 4 'unsigned int' values) with an expression of incompatible type 'int'
stream.c: 151 | vec s3 = NONCE(np);
stream.c: | ^ ~~~~~~~~~
stream.c: stream.c:152:36: error: use of undeclared identifier 'VBPI'
stream.c: 152 | for (iters = 0; iters < inlen/(BPI*64); iters++) {
stream.c: | ^
stream.c: stream.c:91:19: note: expanded from macro 'BPI'
stream.c: 91 | #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: | ^
stream.c: stream.c:152:36: error: use of undeclared identifier 'GPR_TOO'
stream.c: stream.c:91:26: note: expanded from macro 'BPI'
stream.c: 91 | #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: | ^
stream.c: stream.c:155:19: error: use of undeclared identifier 'ONE'
stream.c: 155 | v7 = v3 + ONE;
stream.c: | ^
stream.c: stream.c:176:13: error: call to undeclared function 'ROTW16'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
stream.c: 176 | DQROUND_VECTORS(v0,v1,v2,v3)
stream.c: | ^
stream.c: ...

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	krovetz/vec128
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	krovetz/vec128
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	krovetz/vec128
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	krovetz/vec128
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	krovetz/vec128

Compiler output

Implementation: krovetz/vec128
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

stream.c: stream.c:80:2: error: #error -- Implementation supports only machines with neon, altivec or SSE2
stream.c: #error -- Implementation supports only machines with neon, altivec or SSE2
stream.c: ^~~~~
stream.c: stream.c: In function 'crypto_stream_chacha12_krovetz_vec128_constbranchindex_xor':
stream.c: stream.c:151:14: warning: implicit declaration of function 'NONCE' [-Wimplicit-function-declaration]
stream.c: vec s3 = NONCE(np);
stream.c: ^~~~~
stream.c: stream.c:151:14: error: incompatible types when initializing type 'vec' {aka '__vector(4) unsigned int'} using type 'int'
stream.c: stream.c:91:19: error: 'VBPI' undeclared (first use in this function); did you mean 'BPI'?
stream.c: #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: ^~~~
stream.c: stream.c:152:36: note: in expansion of macro 'BPI'
stream.c: for (iters = 0; iters < inlen/(BPI*64); iters++) {
stream.c: ^~~
stream.c: stream.c:91:19: note: each undeclared identifier is reported only once for each function it appears in
stream.c: #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: ^~~~
stream.c: stream.c:152:36: note: in expansion of macro 'BPI'
stream.c: for (iters = 0; iters < inlen/(BPI*64); iters++) {
stream.c: ^~~
stream.c: stream.c:91:26: error: 'GPR_TOO' undeclared (first use in this function)
stream.c: #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: ^~~~~~~
stream.c: stream.c:152:36: note: in expansion of macro 'BPI'
stream.c: for (iters = 0; iters < inlen/(BPI*64); iters++) {
stream.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128