[Page version: 20241120 00:22:57]
Measurements for armeabi, berry2, crypto_stream Test results for armeabi, berry2, crypto_stream Test results for crypto_stream/speck128256ctrstream.c: In file included from Intrinsics_NEON_128block.h:5, stream.c: from Speck128256NEON.h:16, stream.c: from stream.c:20: stream.c: stream.c: In function 'Encrypt': stream.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:658:1: error: inlining failed in call to 'always_inline' 'vaddq_u64': target specific option mismatch stream.c: 658 | vaddq_u64 (uint64x2_t __a, uint64x2_t __b) stream.c: | ^~~~~~~~~ stream.c: In file included from Speck128256NEON.h:16, stream.c: from stream.c:20: stream.c: Intrinsics_NEON_128block.h:18:13: note: called from here stream.c: 18 | #define ADD vaddq_u64 stream.c: | ^ stream.c: Intrinsics_NEON_128block.h:24:33: note: in expansion of macro 'ADD' stream.c: 24 | #define SET2(X,c) (SET1(X,c), X=ADD(X,SET(0x1,0x0)),c+=2) stream.c: | ^~~ stream.c: stream.c:115:24: note: in expansion of macro 'SET2' stream.c: 115 | SET1(X[0],nonce[1]); SET2(Y[0],nonce[0]); stream.c: | ^~~~ stream.c: In file included from Intrinsics_NEON_128block.h:5, stream.c: from Speck128256NEON.h:16, stream.c: from stream.c:20: stream.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:7203:1: error: inlining failed in call to 'always_inline' 'vcombine_u64': target specific option mismatch stream.c: 7203 | vcombine_u64 (uint64x1_t __a, uint64x1_t __b) stream.c: | ^~~~~~~~~~~~ stream.c: In file included from Speck128256NEON.h:16, stream.c: ...
Implementation | Compiler |
T:neon | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
T:neon | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
T:neon | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
T:neon | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |