Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHRN (4S)

Test 1: uops

Code:

  sqrshrn v0.4h, v0.4s, #3
  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)03090b18191e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722000000612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303723000000612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303723000000612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
10043037230000001032547251000100010003981603018303730372413328951000100010003037303711100110000000073116222629100030383038303830383038
1004303723000000612547251000100010003981603018303730372414328951000100010003037303711100110000000073116222629100030383038303830383038
1004303723000000612547251000100010003981603018303730372414328951150100010003037303711100110000000073116112629100030383038303830383038
1004303722000000612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303723000000612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
10043037230000120612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303723000000612547251000100010003981603018303730372414328951000100010003037303711100110000000094116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshrn v0.4h, v0.4s, #3
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300000000061295474310100100100081231000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100200000071011611296330100001003003830038314973003830372
10204304672442001121111911760138295472510100100100001001000050042771600300180300373003728264328739101162001000020010000300373003711102011009910010010000100000206071011611296330100001003003830038300383003830038
102043003724100100000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003013430182300383003830038
102043003724100000000061295472510125125100001251000062642771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296690100001003003830038300383003830038
10204300372410000001170161295472510100100100001001000050042771600300540300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003723300000000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003723200000000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000071012511296330100001003003830038300383003830038
10204300372330000001440061295472510100100100001001000050042771601300180300373008528264328763101002001000020010000300373003711102011009910010010000100000100071021611297036100001003003830038300383003830038
102043003723300100000061295472510100125100001251000050042785120307740308523117228271328745101002001049325813809300373008511102011009910010010000100000025751071211711296330100001003008530086300383003830038
1020430037233010000120061295472510100125100081001000050042771600308460300863003728264328796101002001000020010000300373003711102011009910010010000100000002858271011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030918191e1f3f4e51inst 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)9fa0a1a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000006129547251001010100001010000504277160130018300373003728286328767106112010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830273
100243003722500021010329547251001010100071010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000030640216222962910000103003830038300383003830038
1002430037225000006129547801001010100001010000504277160130018300373003728286328767100102210000201000030037300371110021109101010000100000034640216222962910000103003830038300383003830038
100243003722500048061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373017911100211091010100001000000120640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000640316222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037225000006129529251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000030640216222962910000103003830038300383003830038
100243003722501000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000001260640216222962910000103003830038300383003830038
100243003722500000726295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000900640216222962910000103003830038300863003830038
10024300372240000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000180640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqrshrn v0.4h, v8.4s, #3
  sqrshrn v1.4h, v8.4s, #3
  sqrshrn v2.4h, v8.4s, #3
  sqrshrn v3.4h, v8.4s, #3
  sqrshrn v4.4h, v8.4s, #3
  sqrshrn v5.4h, v8.4s, #3
  sqrshrn v6.4h, v8.4s, #3
  sqrshrn v7.4h, v8.4s, #3
  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)03080918191e1f3f51inst 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)72scheduler 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)9fa1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000000030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010000000011151181160020036800001002004020040200402004020040
802042003915000000030258010810080008100801265006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915000000030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915000000030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010000100011151180160020036800001002004020040200402004020040
802042003915000000030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500000003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000000123011151180160020036800001002004020040200402004020040
80204200391500001147030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915000000030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915000000030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100004800011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001010050209169142003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001003605020101611142003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020161615112003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001008105020141615152003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020131613162003680000102004020090200902004020091
80024200391500272125800101080000108000050640000020020020039200399996310019800102080000208000020039200392180021109101080000100005020151613132003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100005020111613162003680000102004020040200912004020040
800242003915004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100005020101616162003680000102004020040200402004020040
8002420039150070525800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020141611152003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020151615122003680000102004020040200402004020040