Apple M1 Microarchitecture Research by Dougall Johnson

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

MUL (by element, 4S)

Test 1: uops

Code:

  mul v0.4s, v0.4s, 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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073316112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722015625482510001000100039831313018303730372415328951000100020003037303711100110000373116112630100030383038303830383038
100430372208225482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
1004303723010325482510001000100039831303018303730372415328951000100020003037303711100110000095116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  mul v0.4s, v0.4s, 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)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)6061696b6d6edispatch 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225053629548251010010010000100100005004277313103001803003730037282653287451010020010000200200003003730037111020110099100100100001000071061161129634100001003003830038300383003830038
1020430037225044129548251010010010000100100005004277313103001803003730037282653287451010020010000200200003003730037111020110099100100100001000071061161129696100001003003830038300383003830038
1020430037225053629548251010010010000100100005004277313103001803003730037282653287451010020010000200200003003730037111020110099100100100001000071061161129634100001003003830038300383003830038
102043003722506129539251010010010000100100005004277313063001803003730037282653287451010020010000200200003003730037111020110099100100100001000071001161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313063001803003730037282653287451010020010000200200003003730085111020110099100100100001000071061161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313103001803003730037282653287451010020010000200200003003730037111020110099100100100001000071001161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313063001803003730037282653287451010020010000200200003003730037111020110099100100100001000071061161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313103001803003730037282653287451010020010000200200003003730037111020110099100100100001000071001161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313103001803003730037282653287451010020010000200200003003730037111020110099100100100001000071061161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313103001803003730037282653287451010020010000200200003003730037111020110099100100100001000071061161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722509612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640316222963010000103003830038300383003830038
100243003722503612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222969510000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427803113001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612953925100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  mul v0.4s, v1.4s, 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)030818191e1f3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430515229010101329880608229457227102221471007215211341743428409813034230466304712831448289291149023211483235231663051030277111102011009910010010000100121119593921151229994100001003003830038300383003830038
1020430037225100432061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000441061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500015061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250001650126295302510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000495061295482510100100100001001000050042773131300223003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250006061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372240003510128295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500021061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000180221295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500906129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225001506129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372240043206129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250024010329548251001010100161010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225001506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225003306129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500606129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006612162229630010000103003830038300383003830038
100243003722500008929548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225003006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225003306129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  mul v0.4s, v8.4s, v9.s[1]
  mul v1.4s, v8.4s, v9.s[1]
  mul v2.4s, v8.4s, v9.s[1]
  mul v3.4s, v8.4s, v9.s[1]
  mul v4.4s, v8.4s, v9.s[1]
  mul v5.4s, v8.4s, v9.s[1]
  mul v6.4s, v8.4s, v9.s[1]
  mul v7.4s, v8.4s, 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511041711200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915002141258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915001241258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915006941258010010080000100800005006400001200202003920039997339997801252008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420039150042641258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915001241258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a6a8a9acc2cfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000006125800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000502061604720036080000102004020040200402004020040
80024200391500000006125800101080000108000050640000012002020039200399996310019800102080000201600002003920039218002110910108000010000000502031604320036080000102004020040200402004020040
8002420039150000023404025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000502041608420036080000102004020040200402004020040
80024200391500000904025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000503741604420036080000102004020040200402004020040
80024200391500000304025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000502061606620036080000102004020040200402004020040
80024200391500000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000502031606420036080000102004020040200402004020040
80024200391500000304025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000502041603420036080000102004020040200402004020040
80024200391500000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000502041604420036080000102004020040200402004020040
80024200391500000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000502041604420036080000102004020040200402004020040
80024200391500000304025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000502061603720036080000102004020040200402004020040