Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMULH (vector, 4H)

Test 1: uops

Code:

  sqdmulh v0.4h, v0.4h, v1.4h
  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)030b181e3f4e51inst 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300082254825100010001000398313030183037303724153289510001000200030373037111001100000073316222630100030383038303830383038
1004303723000192254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
1004303723000316254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
100430372200061254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383085308530383038
100430372300082254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
1004303723000191254825100010001000398313130183037303724153289510001000200030373037111001100000373216222630100030383038303830383038
1004303722000109254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
100430372200061254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
100430372300061254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
1004303723000199254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqdmulh v0.4h, v0.4h, v1.4h
  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)03080b191f3f4e51inst 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
1020430037225000013029548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500006129548251010010010008100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300843003728265328745101002001000020020000300373003711102011009910010010000100007101162129634100001003003830038300383003830038
102043008522611006129548251010010010000100102985224280027030018300853013428265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500308229548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)9fa0a1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000010329548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000640216222963010000103003830038300383003830038
1002430037225000000212229548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000640316242963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000640216222963010000103003830038300383003830038
10024300372250000006129548251004410100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000640216222963010000103003830038300383003830038
100243003722500007506129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000640216222963010000103003830038300383003830038
100243003722500000072629548251001010100001010000504277313130018300373003728287328767100102010162222000030037300371110021109101010000100000030640316222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqdmulh v0.4h, v1.4h, v0.4h
  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)031e3a3f4e51inst 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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400424295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250261295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225001303295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000113071011611296340100001003003830038300383003830038

1000 unrolls and 10 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)60696d6edispatch 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)9fa1a8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250822954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250612954825100101110000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000640316222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010000270640316222963010000103003830038300383003830085
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640241222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqdmulh v0.4h, v8.4h, v9.4h
  sqdmulh v1.4h, v8.4h, v9.4h
  sqdmulh v2.4h, v8.4h, v9.4h
  sqdmulh v3.4h, v8.4h, v9.4h
  sqdmulh v4.4h, v8.4h, v9.4h
  sqdmulh v5.4h, v8.4h, v9.4h
  sqdmulh v6.4h, v8.4h, v9.4h
  sqdmulh v7.4h, v8.4h, v9.4h
  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)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)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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000511061611200360800001002004020040200402004020040
8020420039150004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150004125801001008000010080000500640788020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011612200360800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200780800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080918191e1f3f51inst 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)9fa0a1a8accfd0icache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481740000004882580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020003163220036080000102004020040200402004020040
8002420039173000000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020003162320036080000102004020040200402004020040
8002420039173000000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020002162320036080000102004020040200402004020040
8002420039173000000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005092002163320036080000102004020040200402004020040
8002420039173001100402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001020005020003162320036080000102004020040200402004020040
8002420039173000000402580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000005020003163320036080000102004020040200402004020040
8002420039161000000402580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000005020003162320036080000102004020040200402004020040
8002420039161000000612580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020003163320036080000102004020040200402004020040
80024200391610000630402580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000005089003162320036080000102004020040200402004020040
8002420039161001000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020002163320036080000102004020040200402004020040