Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINV (4S)

Test 1: uops

Code:

  fminv s0, 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)03081e3f4e51inst 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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000000373216222629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010001000303730371110011000000673216222629100030383038303830383038
100430372300762547251000100010003981600301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fminv s0, 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)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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250124295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250620295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830085
10204300372250457295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250726295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250250295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372240145295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430083225061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010010071011611296330100001003003830038300383003830038
10204300372250103295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e1f3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000822954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250004402954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001640216212962910000103003830038300383003830038
10024300372250005782954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010200640216222962910000103003830038300383003830038
100243003722510012092954725100151010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225092644912954725100181010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250001032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250001242954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250001452954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372240001662954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002210910101000010000640216222962910000103003830038300383003830038
100243008522502101662954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fminv s0, v8.4s
  fminv s1, v8.4s
  fminv s2, v8.4s
  fminv s3, v8.4s
  fminv s4, v8.4s
  fminv s5, v8.4s
  fminv s6, v8.4s
  fminv s7, 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)03080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500000003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
80204200391500000003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000001000111511801620036800001002004020040200402004020040
802042003915000000020225801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
80204200391500000003025801081008000810080020500640132020020320039200399977699908012020080032200800322003920039118020110099100100800001000000030111511801620036800001002004020040200402004020040
80204200391500000003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
80204200391500000003025801081008000810080136500640940020020020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
802042003915000000021825801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
8020420039150000000137625801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402009120040
80204200391500000003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
802042003915000000024225801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000001030111511801620036800001002004020040200402004020040

1000 unrolls and 10 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)5f60696d6edispatch 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)9fa8accfd0d5d6d9ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420040150008225800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000101050200516032200360080000102004020040200402004020040
8002420039150008225800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050200316032200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050200216023200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050200316033200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050200316032200360080000102004020040200402004020040
80024200391506904025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100050200316033200360080000102004020040200402004020040
80024200391500012825800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000102050200216223200360080000102004020040200402004020040
8002420039150006325800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100350200316023200360680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050200316033200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000101050200316033200360080000102004020040200402004020040