Implementation notes: armeabi, bblack, crypto_stream/chacha20

Computer: bblack
Microarchitecture: armeabi; Cortex-A8 (413fc082)
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20230530
Operation: crypto_stream
Primitive: chacha20
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
110832852 0 016903 412 752moon/neon/32clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
110832796 0 012109 452 744moon/neon/32gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
110832792 0 012069 452 744moon/neon/32gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
111242852 0 017223 412 744moon/neon/32clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
111242852 0 017223 412 744moon/neon/32clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
111242852 0 015589 408 744moon/neon/32clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
111242852 0 025695 412 752moon/neon/32clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
111662796 0 013254 456 744moon/neon/32gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
111662788 0 011541 444 744moon/neon/32gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
213322016 0 016391 412 744moon/armv6/32clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
213322016 0 024863 412 752moon/armv6/32clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
213321952 0 010709 444 744moon/armv6/32gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
213332016 0 016391 412 744moon/armv6/32clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
213332016 0 016071 412 752moon/armv6/32clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
213332016 0 014757 408 744moon/armv6/32clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
213741960 0 012426 456 744moon/armv6/32gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
215411960 0 011273 452 744moon/armv6/32gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
215821956 0 011233 452 744moon/armv6/32gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
252901872 0 412330 456 752e/regsgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
258741656 0 410409 444 744e/mergedgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
267071872 0 412330 456 752e/refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
275419052 1120 0862129 73713 12008T:cryptoppg++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
281654046 1440 0857456 74037 12008T:cryptoppg++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
282074593 488 0748998 73253 12008T:cryptoppclang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
296241960 0 411265 452 752e/mergedgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
296652376 0 412834 456 752e/mergedgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
302072708 0 125479 412 760e/regsclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
303322800 0 125579 412 760e/mergedclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
306249762 1120 0864214 73717 12008T:cryptoppg++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
307071424 0 410729 452 752e/regsgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
308749662 1120 0862902 73717 12008T:cryptoppg++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
3087410152 0 124475 412 752dolbeau/generic-gccsimd256clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
308749980 0 122665 408 744dolbeau/generic-gccsimd256clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
3091510152 0 124475 412 752dolbeau/generic-gccsimd256clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
3091610492 0 124491 412 760dolbeau/generic-gccsimd256clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
310826088 0 120411 412 752dolbeau/generic-gccsimd128clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
310826088 0 120411 412 752dolbeau/generic-gccsimd128clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
310825888 0 118577 408 744dolbeau/generic-gccsimd128clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
311246396 0 120395 412 760dolbeau/generic-gccsimd128clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
314989092 804 0754860 73573 12008T:cryptoppclang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
315409092 804 0754860 73573 12008T:cryptoppclang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
315402572 0 116875 412 752e/mergedclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
315402584 0 116571 412 760e/mergedclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
315402572 0 116875 412 752e/mergedclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
315402572 0 115241 408 744e/mergedclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
319579896 804 0755048 73573 12008T:cryptoppclang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
319992756 0 125527 412 760e/refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
343325500 0 128299 412 760dolbeau/arm-neonclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
354158752 0 131547 412 760dolbeau/generic-gccsimd256clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
362076164 0 128955 412 760dolbeau/generic-gccsimd128clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
371651188 0 49933 444 744e/regsgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
390822300 0 116599 412 752e/regsclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
390822300 0 116279 412 760e/regsclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
390822296 0 114965 408 744e/regsclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
391232300 0 116599 412 752e/regsclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
391651404 0 410713 452 752e/refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
397072472 0 411745 452 752e/mergedgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
404152324 0 116303 412 760e/refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
409982008 0 116311 412 752e/refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
409982008 0 116311 412 752e/refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
424571948 0 411217 452 752e/regsgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
424981812 0 114477 408 744e/refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023062720230530
441651176 0 49925 444 744e/refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
480391564 0 410833 452 752e/refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
569564920 0 413689 444 744dolbeau/generic-gccsimd128gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
668305852 0 415141 452 752dolbeau/generic-gccsimd128gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
746646968 0 417446 456 752dolbeau/generic-gccsimd128gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
759136424 0 415749 452 752dolbeau/generic-gccsimd128gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
8512115320 0 425798 456 752dolbeau/generic-gccsimd256gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
8674614768 0 424093 452 752dolbeau/generic-gccsimd256gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
10112112092 0 421381 452 752dolbeau/generic-gccsimd256gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530
10212111616 0 420385 444 744dolbeau/generic-gccsimd256gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023062720230530

Test failure

Implementation: krovetz/vec128
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
error 111

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/vec128

Compiler output

Implementation: dolbeau/arm-neon
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
chacha.c: In file included from chacha.c:11:
chacha.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:28:2: error: "NEON support not enabled"
chacha.c: #error "NEON support not enabled"
chacha.c: ^
chacha.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:48:24: error: 'neon_vector_type' attribute is not supported for this target
chacha.c: typedef __attribute__((neon_vector_type(8))) int8_t int8x8_t;
chacha.c: ^
chacha.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:49:24: error: 'neon_vector_type' attribute is not supported for this target
chacha.c: typedef __attribute__((neon_vector_type(16))) int8_t int8x16_t;
chacha.c: ^
chacha.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:50:24: error: 'neon_vector_type' attribute is not supported for this target
chacha.c: typedef __attribute__((neon_vector_type(4))) int16_t int16x4_t;
chacha.c: ^
chacha.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:51:24: error: 'neon_vector_type' attribute is not supported for this target
chacha.c: typedef __attribute__((neon_vector_type(8))) int16_t int16x8_t;
chacha.c: ^
chacha.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:52:24: error: 'neon_vector_type' attribute is not supported for this target
chacha.c: typedef __attribute__((neon_vector_type(2))) int32_t int32x2_t;
chacha.c: ^
chacha.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:53:24: error: 'neon_vector_type' attribute is not supported for this target
chacha.c: typedef __attribute__((neon_vector_type(4))) int32_t int32x4_t;
chacha.c: ^
chacha.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:54:24: error: 'neon_vector_type' attribute is not supported for this target
chacha.c: typedef __attribute__((neon_vector_type(1))) int64_t int64x1_t;
chacha.c: ^
chacha.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/arm-neon
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/arm-neon
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/arm-neon
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/arm-neon

Compiler output

Implementation: dolbeau/arm-neon
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
chacha.c: In file included from chacha.c:11:
chacha.c: u4.h: In function 'crypto_stream_chacha20_dolbeau_arm_neon_constbranchindex_ECRYPT_encrypt_bytes':
chacha.c: /usr/lib/gcc/arm-linux-gnueabihf/8/include/arm_neon.h:6761:1: error: inlining failed in call to always_inline 'vdupq_n_u32': target specific option mismatch
chacha.c: vdupq_n_u32 (uint32_t __a)
chacha.c: ^~~~~~~~~~~
chacha.c: In file included from chacha.c:94:
chacha.c: u4.h:45:21: note: called from here
chacha.c: uint32x4_t x_15 = vdupq_n_u32(x[15]);
chacha.c: ^~~~~~~~~~~~~~~~~~
chacha.c: In file included from chacha.c:11:
chacha.c: /usr/lib/gcc/arm-linux-gnueabihf/8/include/arm_neon.h:6761:1: error: inlining failed in call to always_inline 'vdupq_n_u32': target specific option mismatch
chacha.c: vdupq_n_u32 (uint32_t __a)
chacha.c: ^~~~~~~~~~~
chacha.c: In file included from chacha.c:94:
chacha.c: u4.h:44:21: note: called from here
chacha.c: uint32x4_t x_14 = vdupq_n_u32(x[14]);
chacha.c: ^~~~~~~~~~~~~~~~~~
chacha.c: In file included from chacha.c:11:
chacha.c: /usr/lib/gcc/arm-linux-gnueabihf/8/include/arm_neon.h:6761:1: error: inlining failed in call to always_inline 'vdupq_n_u32': target specific option mismatch
chacha.c: vdupq_n_u32 (uint32_t __a)
chacha.c: ^~~~~~~~~~~
chacha.c: In file included from chacha.c:94:
chacha.c: u4.h:41:21: note: called from here
chacha.c: uint32x4_t x_11 = vdupq_n_u32(x[11]);
chacha.c: ^~~~~~~~~~~~~~~~~~
chacha.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE dolbeau/arm-neon
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE dolbeau/arm-neon
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE dolbeau/arm-neon
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE dolbeau/arm-neon

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: #error -- Implementation supports only machines with neon, altivec or SSE2
stream.c: ^
stream.c: stream.c:151:14: warning: implicit declaration of function 'NONCE' is invalid in C99 [-Wimplicit-function-declaration]
stream.c: 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: vec s3 = NONCE(np);
stream.c: ^ ~~~~~~~~~
stream.c: stream.c:152:36: error: use of undeclared identifier 'VBPI'
stream.c: for (iters = 0; iters < inlen/(BPI*64); iters++) {
stream.c: ^
stream.c: stream.c:91:19: note: expanded from macro 'BPI'
stream.c: #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: #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: v7 = v3 + ONE;
stream.c: ^
stream.c: stream.c:176:13: warning: implicit declaration of function 'ROTW16' is invalid in C99 [-Wimplicit-function-declaration]
stream.c: DQROUND_VECTORS(v0,v1,v2,v3)
stream.c: ^
stream.c: ...

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

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_chacha20_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:
CompilerImplementations
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