Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

XTN (2D)

Test 1: uops

Code:

  xtn v0.2s, v0.2d
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)03080b18191e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203716000090611686251000100011522645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
1004203715000000611686251000100010002645211201820372037157131895100010001000203720371110011000000106073116111786100020382038203820382038
1004203716000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
1004203715000000821686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382085
1004203717000000611686251000100010002645211201820372037157131895100010001000203720371110011000000006073116111786100020382038203820382038
1004203715000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
1004203715000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
1004203715000000611686251000100010002645211201820372037157131895100010001000203720371110011000000006073116111786100020382038203820382038
1004203716000000611686251000100010002645211201820372037157131895100010001000203720371110011000000003073116111786100020382038203820382038
10042037160000001031686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  xtn v0.2s, v0.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001066420037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715500000480611968625101001001000010010000500284752112001820037200371843831874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382018220038
10204200371550110000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037156000000020871968625101001001000010010000500285131312001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820181200382003820038
10204200371550000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000100071011612197910100001002003820038200382003820038
10204200371550000000611968625101001001000010010000500284752112001820037200371842131874510100216100002001000020037200371110201100991001001000010000100071011611197910100001002003820038200382003820038
102042003715600030001031968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371560000000611968625101001001000012210000500284752112001820037200371842131874510100200100002001000020037200373110201100991001001000010000000071013311197910100001002003820038200382003820038
10204200371550000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037155000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000300100180800357121997223100001002026620265200382022920275

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500001451968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371501301451968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010300640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500001661968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500001661968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640217221978610000102003820038200382003820038
10024200371560018611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  xtn v0.2s, v8.2d
  xtn v1.2s, v8.2d
  xtn v2.2s, v8.2d
  xtn v3.2s, v8.2d
  xtn v4.2s, v8.2d
  xtn v5.2s, v8.2d
  xtn v6.2s, v8.2d
  xtn v7.2s, v8.2d
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)0308181e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151181161120035800001002003920039200392003920039
802042003814900002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151182162220035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151182162220035800001002003920039200392003920039
802042003815000002925801081008007210080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151182161220035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202028003220080032200382003811802011009910010080000100011151182168420097800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151182162120035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151182161220035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151181161220035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151182162120035800001002003920039200392003920039
802042003815000002925801081008000810080020506640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151182161220035800001002003920039200392003920039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)030818191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401550000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010200050200416662003580000102003920039200392003920039
80024200381560000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010001050200316532003580000102003920039200392003920139
80024200381550000039258001010800001080000506400000201002003820038999631001880010208000020800002003820038518002110910108000010001650200347542003580000102003920039200392003920039
80024200381550000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050200316352003580000102003920039200392003920039
80024200381550000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000050200516542003580000102003920039200392003920039
8002420038155000001530258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010001050200316532003580000102003920039200392003920039
80024200381550000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000050200516642003580000102003920039200392003920039
80024200381550000039258001010800001080000506400000200192003820038999631001880010208000020800002003820189118002110910108000010000050200516352003580000102003920039200392003920039
8002420038155000003925800101080000108000050640000020019200382003899962610018800102080000208000020038200381180021109101080000100011850200516362003580000102003920039200392003920039
80024200381610000039258001010800001080000506423040200192003820038999631001880010208000020800002003820038118002110910108000010000050200516362003580000102003920039200392003920039