Apple M1 Microarchitecture Research by Dougall Johnson

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

UMINV (vector, 4S)

Test 1: uops

Code:

  uminv 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)030b1e3f4e51inst 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
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723048612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723002672547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723002912547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110001073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723018612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uminv 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)03080b1e3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
1020430037225004261295472510100100100001001000056142771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500082295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038

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)60696b6d6edispatch stall (70)72scheduler 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000006129547251001010100001010000504277160130018030037300372828673287671001020100002020000300373003711100211091010100001000000006407163329629010000103003830038300383003830038
10024300372240000006129547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250000006129529251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
100243003722500000010329547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250000006129547251001810100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uminv s0, v8.4s
  uminv s1, v8.4s
  uminv s2, v8.4s
  uminv s3, v8.4s
  uminv s4, v8.4s
  uminv s5, v8.4s
  uminv s6, v8.4s
  uminv 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): 0.2506

retire (01)cycle (02)030b1e3f51inst 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
8020420039150005325801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151183160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500014625801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000022251291231120045800001002004920049200502005020050
8020420048150006427801161008001610080028500640196120029200492004899769998680128200800382001600762004820048118020110099100100800001000022251291231120045800001002005020050200492005020049
8020420048150006426801161008001610080028500640196020029200482004999769998680128200800382001600762004820048118020110099100100800001000022251281231120045800001002005020049200492004920050
8020420049150098526801161008001610080028500640196020029200482004899769998680128200800382001600762004820049118020110099100100800001000022251291231120045800001002005020049200502004920049
8020420048150006427801161008001610080028500640196120029200482004899769998680128200800382001600762004820048118020110099100100800001000022251281231120174800001002004920049200492004920049
8020420048150008526801161008001610080028500640196120029200492004999769998680128200800382001600762004920049118020110099100100800001000022251281231120046800001002004920049200502005020049
802042004915000539268011610080016100800285006401960200292004820049997610998680128200800382001600762004820048118020110099100100800001000022251281231120045800001002005020050200492005020049
8020420048150006426801161008001610080028500640196020029200482004999769998680128200800382001600762004820049118020110099100100800001000022251281231120046800001002004920049200492005020050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e3a3f51inst 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)9fa8accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150110217725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050241716516182003680000102004020040200402004020040
800242003915011024725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050241716413162003680000102004020040200402004020040
800242003915011024725800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050241616417162003680000102004020040200402004020040
8002420039150110211025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000101050241516418162003680000102004020040200402004020040
80024200391501102472580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005024816417162003680000102004020040200402004020040
800242003915011024725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050241516417152003680000102004020040200402004020040
800242003915011624725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050241316414122003680000102004020040200402004020040
8002420039150110214225800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050241716417132003680000102004020040200402004020040
8002420039150110224025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050241616418162003680000102004020040200402004020040
800242003915011024725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050241716415162003680000102004020040200402004020040