Apple M1 Microarchitecture Research by Dougall Johnson

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

MUL (vector, 8B)

Test 1: uops

Code:

  mul v0.8b, v0.8b, v1.8b
  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)03070b1e3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300061254825100010001000398313130183037303724153289510001000200030373037111001100000073116132630100030383038303830383038
100430372310061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430842301061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303722000149254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372300361254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372200061254825100010001000398313030183037303724153289510001000200030373037111001100000075116112630100030383038303830383038
1004303722000363254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372200061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372300661254825100010001000398313030183037303724153289510001000200030373037111001100000073116222630100030383038303830383038
100430372310061254825100010001000398313130183037303724153289510001000200030373037111001100000073116212630100030383038303830383038

Test 2: Latency 1->2

Code:

  mul v0.8b, v0.8b, v1.8b
  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)031e1f3f4e51inst 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722511106129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372244806129548251010010010000100100005004277313130018030037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372244206129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722522806129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372242406129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372253306129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722518606129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018030037300372826532874510100200100002002000030037300371110201100991001001000010010007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9facc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250051612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383008530038
1002430037225009612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000668216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001007640216222963010000103003830038300383003830038
1002430037225009612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000942954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250012612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  mul v0.8b, v1.8b, v0.8b
  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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000003671011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000009671011611296340100001003003830038300383003830038
102043003722510612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000009371011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007571011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000971011611296340100001003003830038300383003830038
102043003722500612954825101001001000710010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007271011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000009071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000008471011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000010571011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830084300372826532874510100200100002002000030037300371110201100991001001000010000008471011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e3f4e51inst 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)9fa0a1a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010002600640416562963010000103003830038300383003830038
10024300372250000101295482510010101000010100005042773133001830037300372828732876710163201000020200003003730037111002110910101000010002900640616662963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000290640616642963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010003360640516652963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000231640616562963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010002930640616642963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010002330640516652963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010002982160640516652963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010003060640616562963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000830640616662963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  mul v0.8b, v8.8b, v9.8b
  mul v1.8b, v8.8b, v9.8b
  mul v2.8b, v8.8b, v9.8b
  mul v3.8b, v8.8b, v9.8b
  mul v4.8b, v8.8b, v9.8b
  mul v5.8b, v8.8b, v9.8b
  mul v6.8b, v8.8b, v9.8b
  mul v7.8b, v8.8b, v9.8b
  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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100010051103511120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100010051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000101551101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000951101161120036800001002004020040200402004020040
802042024315000412580100115800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150003972580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101371120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100010051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e1f3f51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000005020616572003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020516762003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000305020716662003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020416462003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001001305020416562003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020816662003680000102004020040200402004020040
80024200391500004025800101080000108000050640000002002020091200391000731001980010208000020160000200392003911800211091010800001000645020716752003680000102004020040200402004020347
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020716752003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200212003920039999631001980010208000020160000200392003911800211091010800001000605020616652003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001001005020616582003680000102004020040200402004020040