Apple M1 Microarchitecture Research by Dougall Johnson

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

SMULL (by element, 2D)

Test 1: uops

Code:

  smull v0.2d, v0.2s, v1.s[1]
  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)031e3f4e51inst 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372206125482510001000100039831330183037303724153289510001000200030373037111001100000073216112630100030383038303830383038
100430372208425482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313301830373037241532895100010002000303730371110011000024073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100050073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000200030373037111001100000473116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  smull v0.2d, v0.2s, v1.s[1]
  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)03080b1e3a3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010149500427731303005430037300372826532874510100200100002002000030037300371110201100991001001000010020071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010030071011611296340100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383022730038
10204300372250000612954825101001001000010010000500427867003001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000550006403163329630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000280606403163329630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000000006403163329630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000000006403163329630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000030006403163329630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000000006403163329630010000103003830038300383003830038
10024300372250000006129548251001010100081010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000020006403163329630010000103003830038300383003830038
100243003722400000061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000330306403163329630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000320306403163329630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000010306403163329630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  smull v0.2d, v1.2s, v0.s[1]
  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)0308090b1e3f4e51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400006129548251010010010000100100005004277313130018300373003728272728741101002001000820020016300373003711102011009910010010000100000000011171801600296470100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282726287411010020010008200200163003730037111020110099100100100001000000030111740124002964618100001003003830038300383003830038
1020430037225000126129548251010010010000100100005004277313030018300373003728272628741101002001000820020016300373003711102011009910010010000100000000011171801600296470100001003003830038300383003830133
102043003722500006129548251010010010000100100005004277313030054300373003728272628741101002001000820020016300373003711102011009910010010000100000100011171701600296460100001003003830038300383003830038
102043003722500024140129548251012110010000100100005004277313130018301333003728272628760101002001000820020016300373013151102011009910010010000100000103011171801600296470100001003003830038300383003830038
1020430037225000276129548251010010010000100100005004277313030018300373003728272728740101002001000820020016300373003711102011009910010010000100000500011171801600296470100001003003830038300383003830038
1020430037225000910329548251010010010000100100005004277313030018300373003728272628740101002001000820020016300373003711102011009910010010000100000100011171701600296460100001003003830038300383003830038
102043003722500006129548631010010010000100100005004277313030018300373003728272728740101002001000820020016300373003711102011009910010010000100000000011171701600296460100001003003830038302263003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038
102043003722400006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640316222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038302273003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100221091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001010640216222963010000103003830038300383003830038
100243003722536129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383008630038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  smull v0.2d, v8.2s, v9.s[1]
  smull v1.2d, v8.2s, v9.s[1]
  smull v2.2d, v8.2s, v9.s[1]
  smull v3.2d, v8.2s, v9.s[1]
  smull v4.2d, v8.2s, v9.s[1]
  smull v5.2d, v8.2s, v9.s[1]
  smull v6.2d, v8.2s, v9.s[1]
  smull v7.2d, v8.2s, v9.s[1]
  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
802042005815004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051102161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150042125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001002051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150023125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001001051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e3a3f51inst 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)9fa8acc5cficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001010050200416342003680000102004020040200402004020040
8002420039150000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050380837342003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000150200416442003680000102004020040200402004020040
8002420039150000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200416342003680000102004020040200402004020040
8002420039150000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001010050200416432003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000050200416442003680000102004020040200402004020040
8002420039150000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001020050200416342003680000102004020040200402004020040
8002420039150000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200416432003680000102004020040200402004020040
8002420039150000402580106128000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001010050200416442003680000102004020040200402004020040
8002420039150000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200316432003680000102004020040200402004020040