Apple M1 Microarchitecture Research by Dougall Johnson

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

SQNEG (scalar, S)

Test 1: uops

Code:

  sqneg s0, s0
  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
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100006073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303721100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg s0, s0
  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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000060061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000100071011611296330100001003003830038300383003830038
1020430037225000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000103071011611296330100001003003830038300383003830038
1020430037225000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000103071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000005000071011611296330100001003003830038300383003830038
1020430037225000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000203071011611296330100001003003830038300383003830038
1020430037224000000061295472510100100100001001000050042771600300543003730037282643287451010020010000200100003003730037111020110099100100100001000000200071011611296330100001003003830038300383003830038
1020430037225000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000003071011611296330100001003003830038300383003830038
1020430037224000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000003071011611296330100001003003830038300383003830038
1020430037225000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000103071011611296330100001003003830038300383003830038
1020430037225000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000103071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e1f3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000822954725100101010000101000050427716003023430131303212830832876710010201000020100003003730037111002110910101000010224000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003006530037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010001000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001000640216222962910000103003830038300383003830038
1002430037225000612953825100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
1002430037224000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010003000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000030640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101015050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqneg s0, s8
  sqneg s1, s8
  sqneg s2, s8
  sqneg s3, s8
  sqneg s4, s8
  sqneg s5, s8
  sqneg s6, s8
  sqneg s7, s8
  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)030818191e1f3a3f51inst 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)9fa0a1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511811600200360800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
80204200391500000001142580108100802081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801601200360800001002004020040201002004020040
8020420039150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000013111511801600200360800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000019111511801600200360800001002004020040200402004020040
80204200391500000004182580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
8020420039150000000722580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511812311200460800001002004920049200492020520155
80204201021500029006445802151008001610080028500640196200292010120102998614998680128200800382028003820107200481180201100991001008000010000013222512912311200460800001002004920049200502005020049
80204200481500000001062780116100800161008002850064019620029200482004899769998680128200800382008003820049200491180201100991001008000010000013222512812311200450800001002004920049200492005020049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b18191e1f3f51inst 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)9fa0a1a6a8a9acc2cdcfd5d6d9dbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100001000050207160061620036010280000102004020040200932009120040
8002420039166000000013925800101080000108000050640000200202003920039999631001980010208000020800002011220130218002110910108000010000000005020616006132003608880000102004020040200402004020040
80024200391500000000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502016160016162003607380000102004020040200402004020040
800242003915000000004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020616001662003607380000102004020040200402004020040
8002420039150000000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000000050201616001672003607380000102004020040200402004020040
800242003915000000004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020616006162003607380000102004020040200402004020040
8002420039150000000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000000050201616001616200360080000102004020040200402004020040
800242003915000000004025800101080000108000050640000200202003920039999631001980010208000020800002003920039218002110910108000010000000005020161600614200360080000102004020040200402004020040
800242003915000000004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020121600173200360080000102004020040200402004020040
800242003915000000004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000000005020161600164200360080000102004020040200402004020040