Apple M1 Microarchitecture Research by Dougall Johnson

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

SMINV (vector, 8B)

Test 1: uops

Code:

  sminv b0, v0.8b
  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)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
100430372327612547251000100010003981603018303730372414328951000100020003037303711100110002073216112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112664100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sminv b0, v0.8b
  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)03191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722502461295472510100100100001001000050042771600300183003730037282643287621027420010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250066295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200203583003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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
1002430037224000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000002512954725100101010000101000050427716003001830037300372828672876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037224000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000120612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000000606402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sminv b0, v8.8b
  sminv b1, v8.8b
  sminv b2, v8.8b
  sminv b3, v8.8b
  sminv b4, v8.8b
  sminv b5, v8.8b
  sminv b6, v8.8b
  sminv b7, v8.8b
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03080b181e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000003025801081008000810080020500640132120020200392003999866999080120200800322001600642003920039118020110099100100800001000011151182161120036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150010030278011610080016100800285006401961200292004920048997610998680128200800382001600762004820049118020110099100100800001000022251283232220046800001002004920049200492004920050
8020420049150000064278011610080016100800285006401961200292004920048997610998680128200800382001600762004920048118020110099100100800001000022251282232220046800001002005020049200492004920049
802042004815000006427801161008001610080028500640196120029200482004899769998680128200800382001600762004820048118020110099100100800001000022251292232220046800001002004920050200502004920050
8020420048150000064268011610080016100800285006401961200292004920048997610998680128200800382001600762004920049118020110099100100800001000022251282232220046800001002005020050200502004920049
80204200491500000106268011610080016100800285006401961200292004820049997610998680128200800382001600762004920049118020110099100100800001000022251282232220045800001002005020050200492004920049
802042004815000006426801161008001610080028500640196120029200492004999769998680128200800382001600762004920048118020110099100100800001000022251292232220046800001002004920049200492004920050
802042004815000006426801161008001610080028500640196120029200482004999769998680128200800382001600762004820048118020110099100100800001000022251282232220045800001002004920049200492004920050
802042004915000006426801161008001610080028500640196120029200492004899769998680128200800382001600762004820048118020110099100100800001000022251282232220045800001002005020050200492004920049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b191e1f3a3f51inst 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)9fa1a8cdcfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500000004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010000502052116112003680000102004020040200402004020040
800242003915000036004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000502052116112003680000102004020040200402004020040
80024200391500000004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000502052116112003680000102004020040200402004020040
800242003915000024004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000502052116112003680000102004020040200402004020040
80024200391560000008225800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000502052116112003680000102004020040200402004020040
8002420039150000219004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000502052116112003680000102004020040200402004020040
80024200391500000004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000502054116112003680000102004020040200402004020040
8002420039150000249004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000502054116112003680000102004020040200402004020040
80024200391500000004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000502054116112003680000102004020040200402004020040
80024200391500000004025800101080000108000050640000052002020039200399996310019800102080000201600002003920039118002110910108000010000502050116112003680000102004020040200402004020040