Apple M1 Microarchitecture Research by Dougall Johnson

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

SQXTUN (8H)

Test 1: uops

Code:

  sqxtun v0.8b, v0.8h
  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)031e3f4e51inst 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
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372208225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722876125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723015625472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqxtun v0.8b, v0.8h
  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)0308181e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100011271011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100001571011611296330100001003003830038300383003830038
1020430037224000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100010071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010009071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010008071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010009071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010008071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010007071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010007071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500001200612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500002700612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000600612954725100101010000101000050427716003001830037300372828632876710010201016820100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006692162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372240000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqxtun v0.8b, v8.8h
  sqxtun v1.8b, v8.8h
  sqxtun v2.8b, v8.8h
  sqxtun v3.8b, v8.8h
  sqxtun v4.8b, v8.8h
  sqxtun v5.8b, v8.8h
  sqxtun v6.8b, v8.8h
  sqxtun v7.8b, v8.8h
  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)03070a1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150110512580108100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100010511151181161120036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010036011151181161220036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040
802042003915011273025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000011151331161120036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001001311151181161120036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050208167172003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050206167142003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001035350208161762003680000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502016168172003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000102405020171617172003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010260502017166172003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019801172080000208000020039200391180021109101080000100050206161782003680000102004020040200402004020040
800242003915007540258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020171617172003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010072502017161782003680000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502017161762003680000102004020040200402004020040