diff --git a/benchmarks.csv b/benchmarks.csv
index 6064966e..14d27ddd 100644
--- a/benchmarks.csv
+++ b/benchmarks.csv
@@ -46,13 +46,13 @@ cross-sha3-r-sdpg-1-small (10 executions),ref,290135,287741,297757,102853622,102
cross-sha3-r-sdpg-3-fast (10 executions),ref,627948,625525,637639,43573841,43565461,43582933,27513830,27493024,27525746
cross-sha3-r-sdpg-5-fast (10 executions),ref,1146280,1142409,1153794,93557878,93547167,93566329,59948216,59857434,60043852
dilithium2 (1000 executions),clean,1874167,1827645,1914566,7493877,3321630,40762756,2062795,2062255,2063222
-dilithium2 (1000 executions),m4f,1426036,1379636,1466394,3807970,1813656,18528070,1417745,1417203,1418192
+dilithium2 (1000 executions),m4f,1425723,1379410,1466445,3835095,1813682,16068642,1421307,1420219,1422056
dilithium2 (1000 executions),m4fstack,1801523,1684895,1902114,12170976,3900911,86281518,3241353,3194028,3281144
dilithium3 (1000 executions),clean,3205551,3204090,3207411,12696585,5097364,74392293,3376992,3376581,3377393
-dilithium3 (1000 executions),m4f,2515969,2514498,2517634,5884832,2917322,25268693,2411257,2410858,2411717
+dilithium3 (1000 executions),m4f,2515915,2514307,2517413,6054094,2917316,27829552,2415526,2414696,2416440
dilithium3 (1000 executions),m4fstack,3412759,3406659,3419247,23673016,6733971,145803146,5733307,5688893,5778120
dilithium5 (1000 executions),clean,5341477,5286872,5395822,15710371,7953367,75940093,5609679,5609217,5610183
-dilithium5 (1000 executions),m4f,4275029,4210286,4329519,7977781,4882524,25936176,4185417,4184925,4185896
+dilithium5 (1000 executions),m4f,4275033,4220989,4350945,8349360,4882552,29688762,4192692,4191427,4193764
dilithium5 (1000 executions),m4fstack,5816287,5474236,6115061,33452872,11170780,185259803,9912851,9845789,9981834
falcon-1024 (10 executions),m4-ct,354880005,284902033,635131652,87741288,87506676,87922628,991320,982548,997219
falcon-1024 (10 executions),opt-ct,555202324,284912829,1157528581,87710190,87606677,87841235,993584,983066,997523
@@ -196,13 +196,13 @@ cross-sha3-r-sdpg-1-small,ref,2328,466400,245512,,,,,,
cross-sha3-r-sdpg-3-fast,ref,4032,205080,108236,,,,,,
cross-sha3-r-sdpg-5-fast,ref,6824,398600,213436,,,,,,
dilithium2,clean,38304,51968,36192,,,,,,
-dilithium2,m4f,38296,49416,36220,,,,,,
+dilithium2,m4f,38296,49416,9012,,,,,,
dilithium2,m4fstack,4408,5072,2704,,,,,,
dilithium3,clean,60832,79616,57728,,,,,,
-dilithium3,m4f,60824,68864,57720,,,,,,
+dilithium3,m4f,60824,68864,9880,,,,,,
dilithium3,m4fstack,4408,6608,2704,,,,,,
dilithium5,clean,97696,122724,92940,,,,,,
-dilithium5,m4f,97688,116076,92932,,,,,,
+dilithium5,m4f,97688,116076,11944,,,,,,
dilithium5,m4fstack,4408,8136,2712,,,,,,
falcon-1024,clean,34988,84604,8784,,,,,,
falcon-1024,m4-ct,1156,2508,376,,,,,,
@@ -349,13 +349,13 @@ cross-sha3-r-sdpg-1-small,ref,71.8,74.7,78.4,,,,,,
cross-sha3-r-sdpg-3-fast,ref,71.7,68.2,68.7,,,,,,
cross-sha3-r-sdpg-5-fast,ref,71.1,66.1,66.8,,,,,,
dilithium2,clean,61.0,30.9,52.9,,,,,,
-dilithium2,m4f,79.9,60.6,76.8,,,,,,
+dilithium2,m4f,79.9,60.7,76.6,,,,,,
dilithium2,m4fstack,74.8,55.2,40.8,,,,,,
dilithium3,clean,64.7,31.3,56.8,,,,,,
-dilithium3,m4f,82.3,60.3,79.4,,,,,,
+dilithium3,m4f,82.3,60.7,79.2,,,,,,
dilithium3,m4fstack,77.1,54.6,41.0,,,,,,
dilithium5,clean,67.0,35.7,61.1,,,,,,
-dilithium5,m4f,83.5,65.0,81.7,,,,,,
+dilithium5,m4f,83.5,65.3,81.6,,,,,,
dilithium5,m4fstack,76.1,54.5,42.6,,,,,,
falcon-1024,clean,6.5,0.3,23.7,,,,,,
falcon-1024,m4-ct,7.4,0.4,32.4,,,,,,
@@ -501,13 +501,13 @@ cross-sha3-r-sdpg-1-small,ref,18846,0,208,19054,,,,,
cross-sha3-r-sdpg-3-fast,ref,19689,0,208,19897,,,,,
cross-sha3-r-sdpg-5-fast,ref,18593,0,208,18801,,,,,
dilithium2,clean,8064,0,0,8064,,,,,
-dilithium2,m4f,18596,0,0,18596,,,,,
+dilithium2,m4f,19180,0,0,19180,,,,,
dilithium2,m4fstack,24184,0,0,24184,,,,,
dilithium3,clean,7580,0,0,7580,,,,,
-dilithium3,m4f,18588,0,0,18588,,,,,
+dilithium3,m4f,19188,0,0,19188,,,,,
dilithium3,m4fstack,23448,0,0,23448,,,,,
dilithium5,clean,7808,0,0,7808,,,,,
-dilithium5,m4f,18468,0,0,18468,,,,,
+dilithium5,m4f,19096,0,0,19096,,,,,
dilithium5,m4fstack,23820,0,0,23820,,,,,
falcon-1024,clean,82647,0,0,82647,,,,,
falcon-1024,m4-ct,81825,0,79872,161697,,,,,
diff --git a/benchmarks.md b/benchmarks.md
index ba34c3d9..b8fdfdf3 100644
--- a/benchmarks.md
+++ b/benchmarks.md
@@ -48,13 +48,13 @@
| cross-sha3-r-sdpg-3-fast (10 executions) | ref | AVG: 627,948
MIN: 625,525
MAX: 637,639 | AVG: 43,573,841
MIN: 43,565,461
MAX: 43,582,933 | AVG: 27,513,830
MIN: 27,493,024
MAX: 27,525,746 |
| cross-sha3-r-sdpg-5-fast (10 executions) | ref | AVG: 1,146,280
MIN: 1,142,409
MAX: 1,153,794 | AVG: 93,557,878
MIN: 93,547,167
MAX: 93,566,329 | AVG: 59,948,216
MIN: 59,857,434
MAX: 60,043,852 |
| dilithium2 (1000 executions) | clean | AVG: 1,874,167
MIN: 1,827,645
MAX: 1,914,566 | AVG: 7,493,877
MIN: 3,321,630
MAX: 40,762,756 | AVG: 2,062,795
MIN: 2,062,255
MAX: 2,063,222 |
-| dilithium2 (1000 executions) | m4f | AVG: 1,426,036
MIN: 1,379,636
MAX: 1,466,394 | AVG: 3,807,970
MIN: 1,813,656
MAX: 18,528,070 | AVG: 1,417,745
MIN: 1,417,203
MAX: 1,418,192 |
+| dilithium2 (1000 executions) | m4f | AVG: 1,425,723
MIN: 1,379,410
MAX: 1,466,445 | AVG: 3,835,095
MIN: 1,813,682
MAX: 16,068,642 | AVG: 1,421,307
MIN: 1,420,219
MAX: 1,422,056 |
| dilithium2 (1000 executions) | m4fstack | AVG: 1,801,523
MIN: 1,684,895
MAX: 1,902,114 | AVG: 12,170,976
MIN: 3,900,911
MAX: 86,281,518 | AVG: 3,241,353
MIN: 3,194,028
MAX: 3,281,144 |
| dilithium3 (1000 executions) | clean | AVG: 3,205,551
MIN: 3,204,090
MAX: 3,207,411 | AVG: 12,696,585
MIN: 5,097,364
MAX: 74,392,293 | AVG: 3,376,992
MIN: 3,376,581
MAX: 3,377,393 |
-| dilithium3 (1000 executions) | m4f | AVG: 2,515,969
MIN: 2,514,498
MAX: 2,517,634 | AVG: 5,884,832
MIN: 2,917,322
MAX: 25,268,693 | AVG: 2,411,257
MIN: 2,410,858
MAX: 2,411,717 |
+| dilithium3 (1000 executions) | m4f | AVG: 2,515,915
MIN: 2,514,307
MAX: 2,517,413 | AVG: 6,054,094
MIN: 2,917,316
MAX: 27,829,552 | AVG: 2,415,526
MIN: 2,414,696
MAX: 2,416,440 |
| dilithium3 (1000 executions) | m4fstack | AVG: 3,412,759
MIN: 3,406,659
MAX: 3,419,247 | AVG: 23,673,016
MIN: 6,733,971
MAX: 145,803,146 | AVG: 5,733,307
MIN: 5,688,893
MAX: 5,778,120 |
| dilithium5 (1000 executions) | clean | AVG: 5,341,477
MIN: 5,286,872
MAX: 5,395,822 | AVG: 15,710,371
MIN: 7,953,367
MAX: 75,940,093 | AVG: 5,609,679
MIN: 5,609,217
MAX: 5,610,183 |
-| dilithium5 (1000 executions) | m4f | AVG: 4,275,029
MIN: 4,210,286
MAX: 4,329,519 | AVG: 7,977,781
MIN: 4,882,524
MAX: 25,936,176 | AVG: 4,185,417
MIN: 4,184,925
MAX: 4,185,896 |
+| dilithium5 (1000 executions) | m4f | AVG: 4,275,033
MIN: 4,220,989
MAX: 4,350,945 | AVG: 8,349,360
MIN: 4,882,552
MAX: 29,688,762 | AVG: 4,192,692
MIN: 4,191,427
MAX: 4,193,764 |
| dilithium5 (1000 executions) | m4fstack | AVG: 5,816,287
MIN: 5,474,236
MAX: 6,115,061 | AVG: 33,452,872
MIN: 11,170,780
MAX: 185,259,803 | AVG: 9,912,851
MIN: 9,845,789
MAX: 9,981,834 |
| falcon-1024 (10 executions) | m4-ct | AVG: 354,880,005
MIN: 284,902,033
MAX: 635,131,652 | AVG: 87,741,288
MIN: 87,506,676
MAX: 87,922,628 | AVG: 991,320
MIN: 982,548
MAX: 997,219 |
| falcon-1024 (10 executions) | opt-ct | AVG: 555,202,324
MIN: 284,912,829
MAX: 1,157,528,581 | AVG: 87,710,190
MIN: 87,606,677
MAX: 87,841,235 | AVG: 993,584
MIN: 983,066
MAX: 997,523 |
@@ -200,13 +200,13 @@
| cross-sha3-r-sdpg-3-fast | ref | 4,032 | 205,080 | 108,236 |
| cross-sha3-r-sdpg-5-fast | ref | 6,824 | 398,600 | 213,436 |
| dilithium2 | clean | 38,304 | 51,968 | 36,192 |
-| dilithium2 | m4f | 38,296 | 49,416 | 36,220 |
+| dilithium2 | m4f | 38,296 | 49,416 | 9,012 |
| dilithium2 | m4fstack | 4,408 | 5,072 | 2,704 |
| dilithium3 | clean | 60,832 | 79,616 | 57,728 |
-| dilithium3 | m4f | 60,824 | 68,864 | 57,720 |
+| dilithium3 | m4f | 60,824 | 68,864 | 9,880 |
| dilithium3 | m4fstack | 4,408 | 6,608 | 2,704 |
| dilithium5 | clean | 97,696 | 122,724 | 92,940 |
-| dilithium5 | m4f | 97,688 | 116,076 | 92,932 |
+| dilithium5 | m4f | 97,688 | 116,076 | 11,944 |
| dilithium5 | m4fstack | 4,408 | 8,136 | 2,712 |
| falcon-1024 | clean | 34,988 | 84,604 | 8,784 |
| falcon-1024 | m4-ct | 1,156 | 2,508 | 376 |
@@ -355,13 +355,13 @@
| cross-sha3-r-sdpg-3-fast | ref | 71.7% | 68.2% | 68.7% |
| cross-sha3-r-sdpg-5-fast | ref | 71.1% | 66.1% | 66.8% |
| dilithium2 | clean | 61.0% | 30.9% | 52.9% |
-| dilithium2 | m4f | 79.9% | 60.6% | 76.8% |
+| dilithium2 | m4f | 79.9% | 60.7% | 76.6% |
| dilithium2 | m4fstack | 74.8% | 55.2% | 40.8% |
| dilithium3 | clean | 64.7% | 31.3% | 56.8% |
-| dilithium3 | m4f | 82.3% | 61.4% | 79.4% |
+| dilithium3 | m4f | 82.3% | 60.7% | 79.2% |
| dilithium3 | m4fstack | 77.1% | 54.6% | 41.0% |
| dilithium5 | clean | 67.0% | 35.7% | 61.1% |
-| dilithium5 | m4f | 83.5% | 65.0% | 81.7% |
+| dilithium5 | m4f | 83.5% | 65.3% | 81.6% |
| dilithium5 | m4fstack | 76.1% | 54.5% | 42.6% |
| falcon-1024 | clean | 6.5% | 0.3% | 23.7% |
| falcon-1024 | m4-ct | 7.4% | 0.4% | 32.4% |
@@ -509,13 +509,13 @@
| cross-sha3-r-sdpg-3-fast | ref | 19,689 | 0 | 208 | 19,897 |
| cross-sha3-r-sdpg-5-fast | ref | 18,593 | 0 | 208 | 18,801 |
| dilithium2 | clean | 8,064 | 0 | 0 | 8,064 |
-| dilithium2 | m4f | 18,596 | 0 | 0 | 18,596 |
+| dilithium2 | m4f | 19,180 | 0 | 0 | 19,180 |
| dilithium2 | m4fstack | 24,184 | 0 | 0 | 24,184 |
| dilithium3 | clean | 7,580 | 0 | 0 | 7,580 |
-| dilithium3 | m4f | 18,588 | 0 | 0 | 18,588 |
+| dilithium3 | m4f | 19,188 | 0 | 0 | 19,188 |
| dilithium3 | m4fstack | 23,448 | 0 | 0 | 23,448 |
| dilithium5 | clean | 7,808 | 0 | 0 | 7,808 |
-| dilithium5 | m4f | 18,468 | 0 | 0 | 18,468 |
+| dilithium5 | m4f | 19,096 | 0 | 0 | 19,096 |
| dilithium5 | m4fstack | 23,820 | 0 | 0 | 23,820 |
| falcon-1024 | clean | 82,647 | 0 | 0 | 82,647 |
| falcon-1024 | m4-ct | 81,825 | 0 | 79,872 | 161,697 |