Apple M1 Microarchitecture Research by Dougall Johnson

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

SABD (vector, 16B)

Test 1: uops

Code:

  sabd v0.16b, v0.16b, v1.16b
  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)03191e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)6061696d6edispatch 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)a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300612548251000100010003983130030183037303724153289510001000200030373037111001100000730116222630100030383038303830383038
100430372300612548251000100010003983130030183037303724153289510001000200030373037111001100000730116112630100030383038303830383038
100430372300612548251000100010003983130030183037303724153289510001000200030373037111001100010730116222630100030383038303830383038
100430372300612548251000100010003983130030183037303724153289510001000200030373037111001100000730116112630100030383038303830383038
100430372300612548251000100010003983130030183037303724153289510001000200030373037111001100000730116222630100030383038303830383038
100430372300612548251000100010003983131030183037303724153289510001000200030373037111001100000730116112630100030383038303830383038
100430372300612548251000100010003983130030183037303724153289510001000200030373037111001100000730216222630100030383038303830383038
100430372200612548251000100010003983130030183037303724153289510001000200030373037111001100000730116112630100030383038303830383038
100430372300612548251000100010003983131030183037303724153289510001000200030373037111001100000730116222630100030383038303830383038
100430372300612548251000100010003983131030183037303724153289510001000200030373037111001100000730116222630100030383038303830383038

Test 2: Latency 1->2

Code:

  sabd v0.16b, v0.16b, v1.16b
  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)030818191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000006129548251010010010000100100005004277313130018300373008828268328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000072629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000044129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000251295482510100100100001001000050042773131300183003730037282652528745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000157412947620310204141100481541119273642877131303783046430470282964328894108722341148922922986304643046710110201100991001001000010040210166682909172212990334100001003046630464304663037030469
10204301802281109118888006518294672001023714810080149113417534289526130342304623022628298482888911638234111632212297630511304671011020110099100100100001002201227940292611611296340100001003008530133301823022830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372240000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000044629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372240061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722506361295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001003640316332969710000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372240061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sabd v0.16b, v1.16b, v0.16b
  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)0318191e3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250001426295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225003961295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225003061295482510100100100001001000050042773130300180300373003728265328745101002001016720020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773131300180300373003728265328745101002001000020020000300373003711102011009910010010000100000971011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100001071011611296340100001003003830038300383003830038
102043003722500361295482510100100100001001000050042773130300180300373008428265328745101002001000020020000300373003711102011009910010010000100000071011611297420100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308181e1f3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100120640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225000072629548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130021300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sabd v0.16b, v8.16b, v9.16b
  sabd v1.16b, v8.16b, v9.16b
  sabd v2.16b, v8.16b, v9.16b
  sabd v3.16b, v8.16b, v9.16b
  sabd v4.16b, v8.16b, v9.16b
  sabd v5.16b, v8.16b, v9.16b
  sabd v6.16b, v8.16b, v9.16b
  sabd v7.16b, v8.16b, v9.16b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150124125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000351103162220036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102162220036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392024999733999780100200800002001600002003920039118020110099100100800001000051102162220036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102162220036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102162220036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200801392001600002003920039118020110099100100800001000051102162220036800001002004020040200402004020040
80204200391502014125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102162220036800001002004020040200402004020040
802042003915094125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102162220036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102162220036800001002004020040200402004020040
8020420039150013625801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102162220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e3f51inst 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)9fc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481501040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001005020216112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005020116112003680000102004020040200402004020040
800242003915001240258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005020116112003680000102004020040200402004020040
80024200391500940258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005020116112003680000102004020040200402004020040
800242003915001540258001010800001080000506400001200202009020039999631001980010208000020160000200392003911800211091010800001005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005020116112003680000102004020040200402004020040