Apple M1 Microarchitecture Research by Dougall Johnson

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

SMULL (vector, 2D)

Test 1: uops

Code:

  smull v0.2d, v0.2s, v1.2s
  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)030b3f4e51inst 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)a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241582895100010002000303730371110011000000073116112630100030383038303830383038
100430372202122548251000100010003983130301830373037241532895100010002000303730371110011000010073116112630100030383038303830383038
100430372301512548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000001073116112630100030383038303830383038
100430372201532548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  smull v0.2d, v0.2s, v1.2s
  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)030b191e3f4e51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225005161295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225003061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250015210295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225001561295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225001261295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730085111020110099100100100001000000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225003661295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225002461295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225003061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
102043003722500125667295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250021829548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100090640216222963010000103003830038300383003830038
10024300372250015629548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  smull v0.2d, v1.2s, v0.2s
  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)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)9fa0a8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722502472629548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250306129548251010010010000100100005004277313030018300373003728265328745101002041000020420000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250126129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250009612954825100101010000101000050427731303001830037300832828732876710010201000020200003003730037111002110910101000010006406162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201018020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010206402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722503027612954825100101010000101000050427731303001830037300822828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630110000103003830038300383003830038
10024300372241000612954825100101010000101000067427731303001830037300372828732878610010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  smull v0.2d, v8.2s, v9.2s
  smull v1.2d, v8.2s, v9.2s
  smull v2.2d, v8.2s, v9.2s
  smull v3.2d, v8.2s, v9.2s
  smull v4.2d, v8.2s, v9.2s
  smull v5.2d, v8.2s, v9.2s
  smull v6.2d, v8.2s, v9.2s
  smull v7.2d, v8.2s, v9.2s
  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)0307080a18191e3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511041611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000002002020039200399973399978020820080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000180511011611200360800001002004020040200402004020040
80204200391501000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001002240511011611200360800001002004020040200402004020040
8020420039151000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100430511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100200511011611200360800001002004020040200402004020040
80204200391510000004125802011008000010080000500640000120020200392003999733999780100200800002001600002003920090118020110099100100800001000180511011611200360800001002004020040200402004020040
80204200391501000004125801001008000010080099500640000020020200392003999733999780212200800002001602122003920039118020110099100100800001000180511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100030511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa8a9accfd0d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150003340258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200101601062003680000102004020040200402004020040
8002420039150000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502001016010102003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050201561608122003680000102004020040200402004020040
80024200391500051940258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200101601062003680000102004020040200402004020040
8002420039150001540258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200816010122003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050200101601062003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200101601062003680000102004020040200402004020040
8002420039150201840258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050200101601062003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050200101606102003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200101636102003680000102004020040200402004020040