Apple M1 Microarchitecture Research by Dougall Johnson

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

SADDLV (vector, 4S)

Test 1: uops

Code:

  saddlv d0, v0.4s
  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)03181e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100430372810612547251000100010003981603018303731222414328951000100020003037303711100110000073116112629100030383038303830383038
100430372600612547251000100010003981603018303730372414328951000100020003037303711100110005073116112629100030383038303830383038
100430372600612547251000100010003981603018303730372414328951000100020003037303711100110000373116112629100030383038303830383038
100430372600612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372609612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372700612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372600612547251000100010003981603018303730372414328951000100020003037303711100110004073116112629100030383038303830383038
100430372600612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372600612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372600612547251000100010003981603018303730372414328951000100020003037303711100110003373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  saddlv d0, v0.4s
  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)03181e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500061295472510108100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225000726295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716030018300373003728264328745101002001000020020000300373003711102011009910010010000100003071011611296330100001003008530038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295472510010101000010100005042771600300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225061295472510010101000010100005042771600300180300373003728306328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
10024300372250810295472510010101000010100005042798640300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
10024300372250726295472510010101000010100005042771600300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
10024300372250647295472510010101000010100005042771601300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
10024300372250251295472510010101000010100005042771601300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
10024300372250726295472510010101000010100005042771601300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225061295472510010101000010100005042771600300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  saddlv d0, v8.4s
  saddlv d1, v8.4s
  saddlv d2, v8.4s
  saddlv d3, v8.4s
  saddlv d4, v8.4s
  saddlv d5, v8.4s
  saddlv d6, v8.4s
  saddlv d7, v8.4s
  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)03081e3f51inst 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)9fa1a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491500030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500051258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160120036800001002004020040200402004020040
802042003915000116258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 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)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)9fa8accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050205162342003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050207160342003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000101050203160342003680000102004020040200402004020040
800242003915008225800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050204160462003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050204160472003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050206160462003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000103050207160882003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050205160462003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050203160762003680000102004020040200402004020040
8002420039150081925800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050203160442003680000102004020040200402004020040