sha3.c: permute_n_avx512(): simplify num_rounds logic

bench results (samish across the board)
---------------------------------------
x86-64-avx512-gcc before:
  > make clean all BACKEND=2 && ./bench 10000
  ...
  info: cpucycles: version=20240318 implementation=amd64-pmc persecond=4800000000
  info: backend=avx512 num_trials=10000 src_lens=64,256,1024,4096,16384 dst_lens=32
  function,dst_len,64,256,1024,4096,16384
  sha3_224,28,15.4,7.8,7.8,7.1,7.0
  sha3_256,32,15.4,7.8,7.8,7.6,7.4
  sha3_384,48,15.4,11.6,9.8,9.8,9.7
  sha3_512,64,15.5,15.5,14.5,13.8,13.8
  shake128,32,15.6,7.8,6.9,6.2,6.1
  shake256,32,15.6,7.8,7.9,7.6,7.4

x86-64-avx512-clang before:
  > make clean all CC=clang BACKEND=2 && ./bench 10000
  ...
  info: cpucycles: version=20240318 implementation=amd64-pmc persecond=4800000000
  info: backend=avx512 num_trials=10000 src_lens=64,256,1024,4096,16384 dst_lens=32
  function,dst_len,64,256,1024,4096,16384
  sha3_224,28,21.6,10.8,10.7,9.6,9.5
  sha3_256,32,21.6,10.8,10.7,10.3,10.1
  sha3_384,48,21.5,16.0,13.3,13.2,13.1
  sha3_512,64,21.5,21.2,19.8,18.8,18.7
  shake128,32,21.8,10.8,9.4,8.4,8.2
  shake256,32,21.6,10.8,10.7,10.3,10.1

x86-64-avx512-gcc after:
  > make clean all BACKEND=2 && ./bench 10000
  ...
  info: cpucycles: version=20240318 implementation=amd64-pmc persecond=4800000000
  info: backend=avx512 num_trials=10000 src_lens=64,256,1024,4096,16384 dst_lens=32
  function,dst_len,64,256,1024,4096,16384
  sha3_224,28,15.4,7.8,7.8,7.1,7.0
  sha3_256,32,15.4,7.8,7.8,7.6,7.4
  sha3_384,48,15.4,11.6,9.8,9.8,9.7
  sha3_512,64,15.5,15.5,14.6,13.8,13.8
  shake128,32,15.5,7.8,6.9,6.2,6.1
  shake256,32,15.5,7.8,7.9,7.6,7.4

x86-64-avx512-clang after:
  > make clean all CC=clang BACKEND=2 && ./bench 10000
  ...
  info: cpucycles: version=20240318 implementation=amd64-pmc persecond=4800000000
  info: backend=avx512 num_trials=10000 src_lens=64,256,1024,4096,16384 dst_lens=32
  function,dst_len,64,256,1024,4096,16384
  sha3_224,28,21.5,10.8,10.7,9.6,9.5
  sha3_256,32,21.5,10.8,10.7,10.3,10.0
  sha3_384,48,21.6,16.0,13.3,13.2,13.1
  sha3_512,64,21.5,21.2,19.8,18.8,18.7
  shake128,32,21.7,10.8,9.3,8.3,8.2
  shake256,32,21.7,10.8,10.7,10.3,10.1

1 files changed, 2 insertions, 5 deletions

diff --git a/sha3.c b/sha3.c
index b846719..9b213d0 100644
--- a/sha3.c
+++ b/sha3.c
@@ -343,7 +343,7 @@ static inline void permute_n_avx512(uint64_t s[static 25], const size_t num_roun
           r4 = _mm512_maskz_loadu_epi64(0x1f, s + 20); // row 4
 
   // loop over rounds
-  for (size_t i = 0; i < num_rounds; i++) {
+  for (size_t i = (SHA3_NUM_ROUNDS - num_rounds); __builtin_expect(i < SHA3_NUM_ROUNDS, 1); i++) {
     // theta
     {
       // permute ids
@@ -506,11 +506,8 @@ static inline void permute_n_avx512(uint64_t s[static 25], const size_t num_roun
 
     // iota
     {
-      // calculate RCS offset
-      const size_t ofs = SHA3_NUM_ROUNDS - num_rounds + i;
-
       // xor round constant to first cell
-      r0 = _mm512_mask_xor_epi64(r0, 1, r0, _mm512_maskz_loadu_epi64(1, RCS + ofs));
+      r0 = _mm512_mask_xor_epi64(r0, 1, r0, _mm512_maskz_loadu_epi64(1, RCS + i));
     }
   }