Apple M1 Microarchitecture Research by Dougall Johnson

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

SQNEG (vector, 4H)

Test 1: uops

Code:

  sqneg v0.4h, v0.4h
  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)6061696d6edispatch 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)a8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816000301830373037241432895100010001000303730371110011000007300116112629100030383038303830383038
100430372306125472510001000100039816000301830373037241432895100010001000303730371110011000007300116112629100030383038303830383038
100430372306125472510001000100039816000301830373037241432895100010001000303730371110011000007300116112629100030383038303830383038
100430372306125472510001000100039816000301830373037241432895100010001000303730371110011000207300116112629100030383038303830383038
100430372306125472510001000100039816000301830373037241432895100010001000303730371110011000037300116112629100030383038303830383038
100430372336125472510001000100039816000301830373037241432895100010001000303730371110011000007300116112629100030383038303830383038
100430372206125472510001000100039816000301830373037241432895100010001000303730371110011000007300116112629100030383038303830383069
100430372306125472510001000100039816000301830373037241432895100010001000303730371110011000037300116112629100030383038303830383038
100430372306125472510001000100039816000305430373037241432895100010001000303730371110011000007300116112629100030383038303830383038
100430372306125472510001000100039816005301830373037241432895100010001000303730371110011000007300116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg v0.4h, v0.4h
  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)030708090b18191e1f3f4e51inst 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
1020430037225000000001242954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021611296330100001003003830038300383003830082
1020430037224000000004722954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000000004342954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021711296330100001003003830038300383003830038
10204300372250000000016842954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000000001262954725101001131000010010000500427716013001830037300372826432881810427200100002001000030037300371110201100991001001000010000000071021711296330100001003003830038300383003830038
1020430037225000000008102954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372240000000016629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710117222963325100001003003830038300383003830038
102043003722500000000822954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000000005102954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372250000000014632954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038

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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000660082295472510010101000010100005042771600300183003730037282863287671016020100002010000300373003711100211091010100001000010006402162229629010000103003830038300383008530038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001020000006402162229629010000103003830038300383003830038
10024300372250000120061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000120061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000441295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000010006402162229629010000103003830038300383003830086
1002430037225000090061295472510010101000010100005042771600300183003730037282863287671016220100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000306402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqneg v0.4h, v8.4h
  sqneg v1.4h, v8.4h
  sqneg v2.4h, v8.4h
  sqneg v3.4h, v8.4h
  sqneg v4.4h, v8.4h
  sqneg v5.4h, v8.4h
  sqneg v6.4h, v8.4h
  sqneg v7.4h, v8.4h
  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)031e1f3f51inst 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)9fa0a1a6a8a9acc5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118116020036800001002004020040200402004020040
802042003915090302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000031115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016120036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
80204200391501205125801081008000810080020500640132120020201932003999776999080120200801422028013120098200392180201100991001008000010000010151115137026120076800001002014320091200912010020040
8020420101150120302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200909977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200939977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212006120039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)6061696d6edispatch 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)9fa0a1a8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000000006125800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020316332003680000102004020040200402004020040
8002420039150000000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020316332003680000102004020040200402004020040
8002420039149000000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100010305020316322003680000102004020040200402004020040
8002420039150000000004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020216232003680000102004020040200402004020040
8002420039151000000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020216232003680000102004020040200402004020040
8002420039150000000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020216332003680000102004020040200402004020040
800242003915000000000118625800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000005020316332003680000102004020040200402004020040
8002420039150000000004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100010005020316332003680000102004020040200402004020040
80024200391500000000012425800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020216332003680000102004020040200402004020040
80024200391500000000014525800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020316232003680000102004020040200402004020040