Apple M1 Microarchitecture Research by Dougall Johnson

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

XTN (4S)

Test 1: uops

Code:

  xtn v0.4h, v0.4s
  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)03181e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037160786116862510081000100026452102018203720371571318951000100010002037203711100110000073316221786100020382038203820382038
10042037160015616862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203721100110000073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037160027116862510001000100026452102018203720371571318951000100010002037203711100110000373216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  xtn v0.4h, v0.4s
  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)9fa6a8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420323164101481056440500019642182102441401009614611368718285747312001820037200371842131874510426226113302301099820466203237110201100991001001000010000000087004811119791100001002041520371204672042220409
1020420467164010000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001007601000071001161119791100001002003820038200382003820038
10204200371550000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038
1020420037156000000089196863010100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000007100139531119791100001002003820038200382003820038
102042003716100000004811968625101001001000010010000500284752112001820037200371842131874510100200100002001016720037200371110201100991001001000010000000071001161119791100001002003820038200382003820038
10204200371550000012006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100009600071001161119791100001002003820038200382003820038
10204200371550000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000900071001161119791100001002003820038200382003820038
10204200371550000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000900071001161119791100001002003820038200382003820038
102042003715500000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100001500071001161119791100001002003820038200382003820038
10204200371560000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b191e1f3f4e51inst 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)9fa1a3a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037156000000611968625100101010000101000050284752102001820084200851844331876710010201000020100002003720037111002110910101000010000006403162219786010000102003820038200382003820038
1002420037155000012018271968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000606402162219786010000102003820038200382003820038
10024200371550000004231968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010001006402162219786010000102003820038200382003820038
1002420037156000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000306402162219786010000102003820038200382003820038
1002420037155000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037155000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037155000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037155000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371550000001031968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037155000000891968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  xtn v0.4h, v8.4s
  xtn v1.4h, v8.4s
  xtn v2.4h, v8.4s
  xtn v3.4h, v8.4s
  xtn v4.4h, v8.4s
  xtn v5.4h, v8.4s
  xtn v6.4h, v8.4s
  xtn v7.4h, v8.4s
  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)03080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057155000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038156000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000090111511801600200350800001002003920039200392003920039
802042003815500000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000001320111511801600200350800001002003920039200392003920039
8020420038155000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000002000111511801600200350800001002003920039200392003920039
8020420038155000000292580108100800081008002050064013212001920038200389977699868012020080032200800322003820038118020110099100100800001000000000111511801610200350800001002003920039200392003920039
8020420038156000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001000111511801600200350800001002003920039200392003920039
8020420038156000090292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000030111511801600200350800001002003920039200392003920039
8020420038155000000712580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000004000111511801600200350800001002003920039200392003920039
8020420038156000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000002000111511801600200350800001002003920039200392003920039
8020420038155000000522580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000007030111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e3f51inst 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)60696b6d6edispatch 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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015500039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001010005020316632003580000102003920039200392003920039
800242003815510039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001010005020216232003580000102003920039200392003920090
800242003815510039258001010800921080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001010005020316322003580000102003920039200392003920039
800242003815500067258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001010005020616632003580000102003920039200392003920039
800242003815600039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000005020316262003580000102003920039200392003920039
80024200381560037881258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000005020516332003580000102003920039200392003920039
800242003815500081258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000005020616662003580000102003920039200392003920194
800242003815500039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001020005020316562003580000102003920039200392003920039
800242003815600039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001010005020616562003580000102003920039200392003920039
800242003816600039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001010005020316322003580000102003920039200392003920039