Implementation notes: armeabi, bblack, crypto_stream/aes256ctr

Computer: bblack
Microarchitecture: armeabi; Cortex-A8 (413fc082)
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20240425
Operation: crypto_stream
Primitive: aes256ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
47288288 0 011221 484 744T:opensslgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024050520240425
47456184 0 09473 476 744T:opensslgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024050520240425
47496316 0 023662 440 752T:opensslclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024050520240425
47540316 0 014910 440 752T:opensslclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024050520240425
47544316 0 015230 440 744T:opensslclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024050520240425
47624196 0 010025 484 744T:opensslgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024050520240425
47956316 0 015230 440 744T:opensslclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024050520240425
47960186 0 010001 484 744T:opensslgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024050520240425
48120312 0 013564 436 744T:opensslclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024050520240425
8770411371 1036 0746724 73017 11976T:cryptoppclang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024050520240425
8778811371 1036 0746724 73017 11976T:cryptoppclang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024050520240425
8799613523 1404 0852177 72825 11976T:cryptoppg++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024050520240425
884528004 744 0742070 73013 11976T:cryptoppclang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024050520240425
884925595 1484 0845324 73201 11976T:cryptoppg++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024050520240425
9141214955 1404 0854698 72841 11976T:cryptoppg++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024050520240425
9166414625 1404 0852982 72841 11976T:cryptoppg++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024050520240425
9220811431 1036 0746180 73017 11976T:cryptoppclang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024050520240425

Compiler output

armv8crypto.c: In file included from armv8crypto.c:11:
armv8crypto.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:28:2: error: "NEON support not enabled"
armv8crypto.c: #error "NEON support not enabled"
armv8crypto.c:  ^
armv8crypto.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
armv8crypto.c: typedef __attribute__((neon_vector_type(8))) int8_t int8x8_t;
armv8crypto.c:                        ^
armv8crypto.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
armv8crypto.c: typedef __attribute__((neon_vector_type(16))) int8_t int8x16_t;
armv8crypto.c:                        ^
armv8crypto.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
armv8crypto.c: typedef __attribute__((neon_vector_type(4))) int16_t int16x4_t;
armv8crypto.c:                        ^
armv8crypto.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
armv8crypto.c: typedef __attribute__((neon_vector_type(8))) int16_t int16x8_t;
armv8crypto.c:                        ^
armv8crypto.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
armv8crypto.c: typedef __attribute__((neon_vector_type(2))) int32_t int32x2_t;
armv8crypto.c:                        ^
armv8crypto.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
armv8crypto.c: typedef __attribute__((neon_vector_type(4))) int32_t int32x4_t;
armv8crypto.c:                        ^
armv8crypto.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
armv8crypto.c: typedef __attribute__((neon_vector_type(1))) int64_t int64x1_t;
armv8crypto.c:                        ^
armv8crypto.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
T:dolbeau/armv8cryptoclang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE (4.2.1_Compatible_Clang_7.0.1_(tags/RELEASE_701/final))
T:dolbeau/armv8cryptoclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE (4.2.1_Compatible_Clang_7.0.1_(tags/RELEASE_701/final))
T:dolbeau/armv8cryptoclang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE (4.2.1_Compatible_Clang_7.0.1_(tags/RELEASE_701/final))
T:dolbeau/armv8cryptoclang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE (4.2.1_Compatible_Clang_7.0.1_(tags/RELEASE_701/final))

Compiler output

armv8crypto.c: armv8crypto.c:54:16: warning: implicit declaration of function 'vaeseq_u8' is invalid in C99 [-Wimplicit-function-declaration]
armv8crypto.c:     temp_lds = armv8_aese_sbox(rotl_aes_edrk);
armv8crypto.c:                ^
armv8crypto.c: armv8crypto.c:31:45: note: expanded from macro 'armv8_aese_sbox'
armv8crypto.c:         vgetq_lane_u32(vreinterpretq_u32_u8(vaeseq_u8(vreinterpretq_u8_u32(vdupq_n_u32(input)), vzero)),0)
armv8crypto.c:                                             ^
armv8crypto.c: armv8crypto.c:54:16: error: passing 'int' to parameter of incompatible type 'uint8x16_t' (vector of 16 'uint8_t' values)
armv8crypto.c:     temp_lds = armv8_aese_sbox(rotl_aes_edrk);
armv8crypto.c:                ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
armv8crypto.c: armv8crypto.c:31:45: note: expanded from macro 'armv8_aese_sbox'
armv8crypto.c:         vgetq_lane_u32(vreinterpretq_u32_u8(vaeseq_u8(vreinterpretq_u8_u32(vdupq_n_u32(input)), vzero)),0)
armv8crypto.c:         ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
armv8crypto.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:6460:21: note: expanded from macro 'vgetq_lane_u32'
armv8crypto.c:   uint32x4_t __s0 = __p0; \
armv8crypto.c:                     ^~~~
armv8crypto.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:33791:49: note: passing argument to parameter '__p0' here
armv8crypto.c: __ai uint32x4_t vreinterpretq_u32_u8(uint8x16_t __p0) {
armv8crypto.c:                                                 ^
armv8crypto.c: armv8crypto.c:67:16: warning: implicit declaration of function 'vaeseq_u8' is invalid in C99 [-Wimplicit-function-declaration]
armv8crypto.c:     temp_lds = armv8_aese_sbox(tmp11);
armv8crypto.c:                ^
armv8crypto.c: armv8crypto.c:31:45: note: expanded from macro 'armv8_aese_sbox'
armv8crypto.c:         vgetq_lane_u32(vreinterpretq_u32_u8(vaeseq_u8(vreinterpretq_u8_u32(vdupq_n_u32(input)), vzero)),0)
armv8crypto.c:                                             ^
armv8crypto.c: armv8crypto.c:67:16: error: passing 'int' to parameter of incompatible type 'uint8x16_t' (vector of 16 'uint8_t' values)
armv8crypto.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
T:dolbeau/armv8cryptoclang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE (4.2.1_Compatible_Clang_7.0.1_(tags/RELEASE_701/final))

Compiler output

armv8crypto.c: In file included from armv8crypto.c:11:
armv8crypto.c: armv8crypto.c: In function 'aesni_encrypt8':
armv8crypto.c: /usr/lib/gcc/arm-linux-gnueabihf/8/include/arm_neon.h:10413:1: error: inlining failed in call to always_inline 'vld1q_u32': target specific option mismatch
armv8crypto.c:  vld1q_u32 (const uint32_t * __a)
armv8crypto.c:  ^~~~~~~~~
armv8crypto.c: armv8crypto.c:166:23: note: called from here
armv8crypto.c:      uint32x4_t nv0i = vld1q_u32((const uint32_t*)n);                  \
armv8crypto.c:                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
armv8crypto.c: armv8crypto.c:191:1: note: in expansion of macro 'FUNC'
armv8crypto.c:  FUNC(8, MAKE8)
armv8crypto.c:  ^~~~
armv8crypto.c: In file included from armv8crypto.c:11:
armv8crypto.c: /usr/lib/gcc/arm-linux-gnueabihf/8/include/arm_neon.h:10998:1: error: inlining failed in call to always_inline 'vst1q_u64': target specific option mismatch
armv8crypto.c:  vst1q_u64 (uint64_t * __a, uint64x2_t __b)
armv8crypto.c:  ^~~~~~~~~
armv8crypto.c: armv8crypto.c:173:7: note: called from here
armv8crypto.c:        vst1q_u64((uint64_t*)n, vaddq_u64(vreinterpretq_u64_u32(nv0i), vsetq_pair_u64(N,1))); \
armv8crypto.c:        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
armv8crypto.c: armv8crypto.c:191:1: note: in expansion of macro 'FUNC'
armv8crypto.c:  FUNC(8, MAKE8)
armv8crypto.c:  ^~~~
armv8crypto.c: In file included from armv8crypto.c:11:
armv8crypto.c: /usr/lib/gcc/arm-linux-gnueabihf/8/include/arm_neon.h:642:1: error: inlining failed in call to always_inline 'vaddq_u64': target specific option mismatch
armv8crypto.c:  vaddq_u64 (uint64x2_t __a, uint64x2_t __b)
armv8crypto.c:  ^~~~~~~~~
armv8crypto.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
T:dolbeau/armv8cryptogcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE (8.3.0)
T:dolbeau/armv8cryptogcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE (8.3.0)
T:dolbeau/armv8cryptogcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE (8.3.0)
T:dolbeau/armv8cryptogcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE (8.3.0)