Implementation notes: aarch64, pi3bplus, crypto_hash/blake2s

Computer: pi3bplus
Microarchitecture: aarch64; Cortex-A53 (410fd034)
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20230530
Operation: crypto_hash
Primitive: blake2s

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
15125	10232 0 0	21774 888 744	`T:regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
15125	10232 0 0	23055 896 760	`T:regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
15500	10324 0 0	23888 824 752	`T:regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
17750	7296 0 0	20191 896 760	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
17750	10832 0 0	21462 872 736	`T:regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
21125	6596 0 0	18271 896 744	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
23875	6636 0 0	17383 880 736	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
25500	9276 0 0	22824 824 752	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230602	20230530
57500	7912 0 0	19519 896 744	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530
61500	13944 0 0	25430 888 744	`T:regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230602	20230530

Compiler output

Implementation: T:avxicc
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

blake2s.S: blake2s.S:13:14: error: unknown token in expression
blake2s.S: xorl %r11d, %r11d
blake2s.S: ^
blake2s.S: blake2s.S:13:14: error: invalid operand
blake2s.S: xorl %r11d, %r11d
blake2s.S: ^
blake2s.S: blake2s.S:14:14: error: unknown token in expression
blake2s.S: xorl %ecx, %ecx
blake2s.S: ^
blake2s.S: blake2s.S:14:14: error: invalid operand
blake2s.S: xorl %ecx, %ecx
blake2s.S: ^
blake2s.S: blake2s.S:15:14: error: unknown token in expression
blake2s.S: movq %rsi, %r9
blake2s.S: ^
blake2s.S: blake2s.S:15:14: error: invalid operand
blake2s.S: movq %rsi, %r9
blake2s.S: ^
blake2s.S: blake2s.S:16:38: error: unexpected token in argument list
blake2s.S: vmovdqu .L_2il0floatpacket.10(%rip), %xmm4
blake2s.S: ^
blake2s.S: blake2s.S:17:14: error: unknown token in expression
blake2s.S: xorl %eax, %eax
blake2s.S: ^
blake2s.S: blake2s.S:17:14: error: invalid operand
blake2s.S: ...

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

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

Compiler output

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

blake2s.S: blake2s.c: Assembler messages:
blake2s.S: blake2s.c:13: Error: unknown mnemonic `xorl' -- `xorl %r11d,%r11d'
blake2s.S: blake2s.c:14: Error: unknown mnemonic `xorl' -- `xorl %ecx,%ecx'
blake2s.S: blake2s.c:15: Error: unknown mnemonic `movq' -- `movq %rsi,%r9'
blake2s.S: blake2s.c:16: Error: unknown mnemonic `vmovdqu' -- `vmovdqu .L_2il0floatpacket.10(%rip),%xmm4'
blake2s.S: blake2s.c:17: Error: unknown mnemonic `xorl' -- `xorl %eax,%eax'
blake2s.S: blake2s.c:18: Error: unknown mnemonic `vmovdqu' -- `vmovdqu .L_2il0floatpacket.7(%rip),%xmm0'
blake2s.S: blake2s.c:19: Error: unknown mnemonic `vmovdqa' -- `vmovdqa %xmm4,%xmm2'
blake2s.S: blake2s.c:20: Error: unknown mnemonic `vmovdqu' -- `vmovdqu .L_2il0floatpacket.8(%rip),%xmm1'
blake2s.S: blake2s.c:21: Error: unknown mnemonic `movq' -- `movq %rdx,%r8'
blake2s.S: blake2s.c:22: Error: unknown mnemonic `vmovdqu' -- `vmovdqu .L_2il0floatpacket.9(%rip),%xmm3'
blake2s.S: blake2s.c:23: Error: unknown mnemonic `xorl' -- `xorl %r10d,%r10d'
blake2s.S: blake2s.c:24: Error: unknown mnemonic `vmovdqu' -- `vmovdqu .L_2il0floatpacket.11(%rip),%xmm5'
blake2s.S: blake2s.c:25: Error: unknown mnemonic `cmpq' -- `cmpq $64,%rdx'
blake2s.S: blake2s.c:26: Error: unknown mnemonic `jbe' -- `jbe ..B1.5'
blake2s.S: blake2s.c:28: Error: unknown mnemonic `movq' -- `movq %rbp,-104(%rsp)'
blake2s.S: blake2s.c:29: Error: unknown mnemonic `lea' -- `lea -1(%rdx),%rsi'
blake2s.S: blake2s.c:30: Error: unknown mnemonic `sarq' -- `sarq $5,%rsi'
blake2s.S: blake2s.c:32: Error: unknown mnemonic `movq' -- `movq %rcx,%rbp'
blake2s.S: blake2s.c:33: Error: unknown mnemonic `shrq' -- `shrq $58,%rsi'
blake2s.S: blake2s.c:34: Error: unknown mnemonic `movq' -- `movq %rax,%rcx'
blake2s.S: blake2s.c:35: Error: unknown mnemonic `lea' -- `lea -1(%rsi,%rdx),%rdx'
blake2s.S: blake2s.c:36: Error: unknown mnemonic `sarq' -- `sarq $6,%rdx'
blake2s.S: blake2s.c:37: Error: unknown mnemonic `movq' -- `movq %rdx,%rax'
blake2s.S: blake2s.c:39: Error: unknown mnemonic `vmovdqu' -- `vmovdqu (%rcx,%r9),%xmm9'
blake2s.S: ...

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

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

Compiler output

Implementation: T:regs
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

blake2s.c: blake2s.c:796:11: warning: implicit conversion from 'unsigned long' to 'uint32_t' (aka 'unsigned int') changes value from 18446744073180816980 to 3766232660 [-Wconstant-conversion]
blake2s.c: v14 = ~0x1F83D9ABUL;
blake2s.c: ~ ^~~~~~~~~~~~~
blake2s.c: 1 warning generated.

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

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

Compiler output

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

blake2s.c: blake2s.c: In function 'crypto_hash_blake2s_regs_timingleaks':
blake2s.c: blake2s.c:796:11: warning: conversion from 'long unsigned int' to 'uint32_t' {aka 'unsigned int'} changes value from '18446744073180816980' to '3766232660' [-Woverflow]
blake2s.c: v14 = ~0x1F83D9ABUL;
blake2s.c: ^

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

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

Compiler output

Implementation: T:xmm
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

blake2s.c: In file included from blake2s.c:21:
blake2s.c: ./blake2-config.h:68:2: error: "This code requires at least SSE2."
blake2s.c: #error "This code requires at least SSE2."
blake2s.c: ^
blake2s.c: In file included from blake2s.c:24:
blake2s.c: In file included from /usr/lib/llvm-7/lib/clang/7.0.1/include/emmintrin.h:27:
blake2s.c: In file included from /usr/lib/llvm-7/lib/clang/7.0.1/include/xmmintrin.h:27:
blake2s.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:64:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
blake2s.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
blake2s.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blake2s.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:143:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
blake2s.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
blake2s.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blake2s.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:173:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
blake2s.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
blake2s.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blake2s.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:203:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
blake2s.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
blake2s.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blake2s.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:230:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
blake2s.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
blake2s.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blake2s.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:253:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
blake2s.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
blake2s.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blake2s.c: ...

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

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

Compiler output

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

blake2s.c: In file included from blake2s.c:21:
blake2s.c: blake2-config.h:68:2: error: #error "This code requires at least SSE2."
blake2s.c: #error "This code requires at least SSE2."
blake2s.c: ^~~~~
blake2s.c: blake2s.c:24:10: fatal error: emmintrin.h: No such file or directory
blake2s.c: #include <emmintrin.h>
blake2s.c: ^~~~~~~~~~~~~
blake2s.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	T:xmm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:xmm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:xmm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:xmm

Namespace violations

Implementation: T:ref
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

blake2s-ref.o blake2s T
blake2s-ref.o blake2s_final T
blake2s-ref.o blake2s_init T
blake2s-ref.o blake2s_init_key T
blake2s-ref.o blake2s_init_param T
blake2s-ref.o blake2s_update T

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

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