Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMEQ (vector, zero, 8H)

Test 1: uops

Code:

  fcmeq v0.8h, v0.8h, #0
  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)a8acc2c3cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037151561168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715961168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715661168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037151561168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037153156168625100010001000264521201820372037157131895100010001000203720371110011000001073116111786100020382038203820382038
10042037159141168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037161561168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203716661168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715961168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq v0.8h, v0.8h, #0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001007102162219791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200101672003720037111020110099100100100001007102162319791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001007102162219791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001007102162219791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001007102162219791100001002003820038200382003820038
1020420037150013261196862510100100100001001000052228487851200182003720037184213187451010020010000200100002003720037111020110099100100100001007102162219791100001002003820038200382008520038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001007102162219791100001002003820038200382003820038
1020420037150056161196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001007102162219791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720084184213187451010020010000200100002003720037111020110099100100100001007102162219791100001002003820038200382003820038
10204200371500961196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001007352162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000013001031968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000306402162219786010000102003820038200382003820038
10024200371500100231002511967525100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000010006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000010006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101015250284752102001820037200371844331876710010201000020100002003720037211002110910101000010000000006402242219822010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000007272162219786010000102003820038200382003820038
100242003715000001200611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000010306402162219786010000102003820038200382003820038
100242003715000001200611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000821968645100101010000101000050284752112005420037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000002700611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmeq v0.8h, v8.8h, #0
  fcmeq v1.8h, v8.8h, #0
  fcmeq v2.8h, v8.8h, #0
  fcmeq v3.8h, v8.8h, #0
  fcmeq v4.8h, v8.8h, #0
  fcmeq v5.8h, v8.8h, #0
  fcmeq v6.8h, v8.8h, #0
  fcmeq v7.8h, v8.8h, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 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)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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150100292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150060292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000012251281231120046800001002005020049200492004920049
8020420048150000642680116100800161008002850064019620028200482004899769998680128200800382008003820048200481180201100991001008000010000022251281231120046800001002005020050200502005020050
8020420090150000642680116100800161008002850064019620028200492004899769998680128200800382008003820049200481180201100991001008000010000022251281231520123800001002004920050200502004920049
8020420048150000642680116100800161008002850064019620028200492004999769998680128200800382008003820049200491180201100991001008000010000022251291231120045800001002004920049200492004920049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304091e3f51inst 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)9fa8branch mispredict (cb)cfitlb miss (d4)d5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000085258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020016161717200350080000102003920039200392003920039
80024200381501108525800101080000108000050640000120019200382003899963100188001020800002080000200652003811800211091010800001000502118161816200350080000102003920039200392003920039
800242003815011085258001010800001080000506400001200192003820038999631001880010208000020800002004920038118002110910108000010015020017161717200350080000102003920039200392003920039
80024200381501108525800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502111716169200350080000102003920039200392003920039
800242003815011016925800101080000108000050640000120019200382003899963100188001020800002080000200652003811800211091010800001020502111616179200350080000102003920039200392003920039
800242003815011085258001010800001080000506400001200192003820038999631001880010208000020800002004920038118002110910108000010005021117161716200350080000102003920039200392003920039
800242003815011085258001010800001080000506400001200192003820038999631001880010208000020800002004920038118002110910108000010005021114161717200350080000102003920039200392003920039
800242003815011085258001010800001080000506400001200192003820038999631001880010208000020800002006520038118002110910108000010005021117161714200350080000102003920039200392003920039
80024200381501108525800101080000108000050640000120019200382003899963100188001020800002080000200492003811800211091010800001000502111616917200350080000102003920039200392003920039
800242003815011085258001010800001080000506400001200192003820038999631001880010208000020800002004920038118002110910108000010005021113161017200350080000102003920039200392003920039