W[i] = SIGMA1(W[i-2]) + W[i-7] + SIGMA0(W[i-15]) + W[i-16]; for 16 <= i <= 63 // SIGMA0(x) = ROTR(7,x) XOR ROTR(18,x) XOR SHR(3,x) // SIGMA1(x) = ROTR(17,x) XOR ROTR(19,x) XOR SHR(10,x) #define LOAD1(index) \ MOVW (((index-2)&0xf)*4)(R3), REGTMP4; \ MOVW (((index-15)&0xf)*4)(R3), REGTMP1; \ MOVW (((index-7)&0xf)*4)(R3), REGTMP; \ MOVW REGTMP4, REGTMP2; \ MOVW REGTMP4, REGTMP3; \ ROTR $17, REGTMP4; \ ROTR $19, REGTMP2; \ SRL $10, REGTMP3; \ XOR REGTMP2, REGTMP4; \ XOR REGTMP3, REGTMP4; \ ROTR $7,...

W[i] = SIGMA1(W[i-2]) + W[i-7] + SIGMA0(W[i-15]) + W[i-16]; for 16 <= i <= 63 // SIGMA0(x) = ROTR(7,x) XOR ROTR(18,x) XOR SHR(3,x) // SIGMA1(x) = ROTR(17,x) XOR ROTR(19,x) XOR SHR(10,x) #define LOAD1(index) \ MOVW (((index-2)&0xf)*4)(R3), REGTMP4; \ MOVW (((index-15)&0xf)*4)(R3), REGTMP1; \ MOVW (((index-7)&0xf)*4)(R3), REGTMP; \ MOVW REGTMP4, REGTMP2; \ MOVW REGTMP4, REGTMP3; \ ROTR $17, REGTMP4; \ ROTR $19, REGTMP2; \ SRL $10, REGTMP3; \ XOR REGTMP2, REGTMP4; \ XOR REGTMP3, REGTMP4; \ ROTR $7,...

Nick Butlin, Nishant Shukla, Pengfei Ni, Przemyslaw Tredak, @rasbt, @Ronny,
Rudolf Rosa, @RustingSword, Sam Abrahams, Sam Putnam, @SeongAhJo, Shi Jiaxin,
@skavulya, Steffen MüLler, @TheUSER123, @tiriplicamihai, @vhasanov, Victor
Costan, Vit Stepanovs, Wangda Tan, Wenjian Huang, Xingdong Zuo, Yaroslav
Bulatov, Yota Toyama, Yuan (Terry) Tang, Yuxin Wu