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, 4S)

Test 1: uops

Code:

  sminv 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
10043037230061254725100010001000398160301830373037241432895100010002000303730371110011000015073116112629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722096125472510001000100039816030183037303724143289510001000200030373037111001100003073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372303612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sminv 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)03080e18191e3f4e51inst 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)696b6d6edispatch 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722502000612954725101001001000010010000500427716030018030037300372826432874510100200100002002000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018030037300372826432874510100200100002002000030037300371110201100991001001000010000000078511611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018030037300372826432874510100200100002002000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225000001032954725101001001000010010000500427716030018030037300372826832874510100204100002002000030037300371110201100991001001000010002128298071011622296640100001003003830038300383003830038
1020430037225000012612954725101001001000010010000500427716030018030037300372826432874510100200100002002000030037300852110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225100001032954725101001001000010010000500427716030018030037300372826432874510100200100002002000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018030037300372826432874510100200100002002000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722400210612954725101001001000010010000500427716030018030037300372826432874510426200100002002000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018030037300372826432874510100200100002002000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018030037300372826432874510100200100002002000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0309181e3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722500061295474310018101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722400061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sminv s0, v8.4s
  sminv s1, v8.4s
  sminv s2, v8.4s
  sminv s3, v8.4s
  sminv s4, v8.4s
  sminv s5, v8.4s
  sminv s6, v8.4s
  sminv 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)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)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)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420068150063302580108100800081008002050064013220020200392003999770699908012020080032200160064200882003911802011009910010080000100011151180160020036800001002004020040200402004020040
8020420039150018302580108100800081008002050064013220020200392003999770699908012020080032200160064200392003911802011009910010080000100211151180160120036800001002004020040200402004020040
8020420039150066302580108100800081008002050064013220020200392003999770699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999777699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999770699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
8020420039150054302580108100800081008002050064013220020200392003999770699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
8020420039150045302580108100800081008002050064013220020200392003999770699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999770699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
8020420090150054302580108100800081008002050064013220020200392003999770699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999770699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040

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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015042402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000050201316652003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000502011161152003680000102004020040200402004020040
80024200391506340258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020416552003680000102004020040200402004020040
80024200391505740258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020516642003680000102004020040200402004020040
8002420039150454025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000502011161262003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020616662003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000050203161162003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020416452003680000102004020040200402004020040
80024200391503640258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020516742003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399993310019800102080000201600002003920039118002110910108000010000050204161272003680000102004020040200402004020040