Apple M1 Microarchitecture Research by Dougall Johnson

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

FADD (vector, 2S)

Test 1: uops

Code:

  fadd v0.2s, 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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100018073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000116320003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100012073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037239612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  fadd v0.2s, 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)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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722519612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313130018300373003728265029287631027020010000200203363008830037111020110099100100100001000007101161129634100001003003830038300383003830038

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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250396129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828782876710010201000020200003003730037111002110910101000010300640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fadd v0.2s, 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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000105295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003008330037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500089295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225001561295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830229300383003830038
102043003722500061295482510100100100001001000050042786700300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500082295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000137102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003008530037111020110099100100100001000007102161229634100001003003830133300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640316222963010000103022830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225009612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300863003830038
1002430037225000612954825100101010000101014950427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383008130038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fadd v0.2s, v8.2s, v9.2s
  fadd v1.2s, v8.2s, v9.2s
  fadd v2.2s, v8.2s, v9.2s
  fadd v3.2s, v8.2s, v9.2s
  fadd v4.2s, v8.2s, v9.2s
  fadd v5.2s, v8.2s, v9.2s
  fadd v6.2s, v8.2s, v9.2s
  fadd v7.2s, 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)030b1e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915000412580100100800001008000050064000002002002003920039997339997801002008000020016000020039200891180201100991001008000010010511021611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915010412580100100800001008000050064000012002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002002003920039997339997801002008000020016000020039200391180201100991001008000010013511011611200360800001002004020040200402004020040
802042003914900412580100100800001008000050064000012002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002024620040200402004020040
802042003915000412580100100800001008000050064000012002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002002003920039997339997801002008000020016000020039200391180201100991001008000010010511011611200360800001002004020040200402004020040

1000 unrolls and 10 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)696b6d6edispatch 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)9fa8accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150040258001010800001080000506400002002002003920039999631001980010208000020160000200392003911800211091010800001000502000031611200368680000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020160000200392003911800211091010800001000502000011611200367380000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020160000200392003911800211091010800001000502000011611200367380000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020160208200392003921800211091010800001000502000011611200368880000102004020040200402004020040
8002420039150040258001010800001080000506400002002032003920039999631001980010208000020160000200392003911800211091010800001000502000021622200367380000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020160000200392003911800211091010800001000502000011611200367380000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020160000200392003911800211091010800001000502000021622200367380000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020160000200392003911800211091010800001000502030011611200367380000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020160000200392003911800211091010800001003502000011611200368880000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020160000200392003911800211091010800001003502000011611200367380000102004020040200402004020040