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, H)

Test 1: uops

Code:

  sqneg h0, h0
  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)a6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372396125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723126125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372336125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723456125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg h0, h0
  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)03080918191e1f3f4e51inst 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)9fa0a1a6a8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000171011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011711296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000030071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000100071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030a18191e1f3f4e51inst 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
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000306404165529629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006405164529629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006405165629629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006405165529629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006405165529629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006406165629629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006406166429629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006405165629629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006405166529629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006405165529629010000103003830038300383003830084

Test 3: throughput

Count: 8

Code:

  sqneg h0, h8
  sqneg h1, h8
  sqneg h2, h8
  sqneg h3, h8
  sqneg h4, h8
  sqneg h5, h8
  sqneg h6, h8
  sqneg h7, h8
  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)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)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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581490000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391500000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391500000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
802042003915000000000302580108100800081008002050064013212007020039200399977699908012020080032200800322003920039118020110099100100800001000000350001115118016002003600800001002004020040200402004020040
80204200391500000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118116002003600800001002004020040200402004020040
80204200391500000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391500000060030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
802042003915000040120030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100200000001115118016002003600800001002004020040200402004020040
80204200391500000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391500000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090b191e3f51inst 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000502050116112003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
80024200391500002140258001010800001080000506400000020020200892003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
80024200391500000132258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
80024200391500001240258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
8002420039150000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
80024200391500001240258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040