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, B)

Test 1: uops

Code:

  sqneg b0, b0
  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)033f4e51inst 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
10043037236125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037236125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037226125472510001000100039816003018303730372414328951000100010003037303711100110001073216222629100030383038303830383038
10043037236125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372328425472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037226125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037226125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037236125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037226125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372211525472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg b0, b0
  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)03080b191e1f3f4e51inst 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)9fa0a6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000006129547251010010010000100100005004277160030018030037300372826432874510100200100002001016630037300372110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037224000006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000028300071011611296330100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018030085300372826432874510100200100002001000030133300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037224000006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000184130071011611296330100001003003830038300383003830038
1020430037225010006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372250000081529547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372250000072629547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000090071011611296330100001003003830038300383003830038
10204300372250000072629547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000030071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa1a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243008422500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006403162229629010000103003830038300383003830038
1002430037225002732954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
1002430037225007612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767101642010000201000030037300371110021109101010000100000006402162229629110000103003830038300383003830038
1002430037225021612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000206402162229629010000103003830038300383008530038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629210000103003830038300383013330038

Test 3: throughput

Count: 8

Code:

  sqneg b0, b8
  sqneg b1, b8
  sqneg b2, b8
  sqneg b3, b8
  sqneg b4, b8
  sqneg b5, b8
  sqneg b6, b8
  sqneg b7, b8
  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)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)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)9fa1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220256200391180201100991001008000010000011151180480020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080224200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997726999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a0b18191e1f3a3f51inst 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)9fa0a6a8a9acc2cdcfd0d2d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150100100000247258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024001616161520036080000102004020040200402004020040
8002420039150100100000247258001010800001080000506400000020020200392003999963100198001020801062080000200392003911800211091010800001000000005024001516131720036080000102004020040200402004020040
8002420039150100100000247258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024001516161620036080000102004020040200402004020040
8002420039150100100000247258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024001116151320036080000102004020040200402004020040
8002420039150100100000247258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024001316151920036080000102004020040200402004020040
8002420039150100100000247258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024001316915200365980000102004020040200402004020040
8002420039150100100000247258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024001416161420036080000102004020040200402004020040
800242003915010010000024725800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502400916161420036080000102004020040200402004020040
8002420039150100100000247258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024001416151220036080000102004020040200402004020040
8002420039150100100000247258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024001416161620036080000102004020040200402004020040