Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMLT (scalar, zero, D)

Test 1: uops

Code:

  fcmlt d0, d0, #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)03181e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
10042037150361168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371500128168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371506361168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
10042037151061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371506661168625100010001000264521120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmlt d0, d0, #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)03091e3f4e51inst 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)9fa0a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150033761968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150118611968625101001001000010010000500284752120018200372003718421818763101002021016820010164200372003721102011009910010010000100201007101161119791100001002003820038200382003820038
1020420037150027611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500498611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150024611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037149027611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500302121968625101001001000010310000500284752120018200842003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820084200382003820038
1020420037150005501968625101001091000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000017101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3a3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500006119686251001010100001010000502847521020018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000034619686251001010100001010000502847521020018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500606119686251001010100001010000502847521020162200372003718443031876710010201000020100002003720037211002110910101000010000640216221978610000102003820038200382003820038
10024200371500006119686251001010100001010000502847521020018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371501006119686251001010100001010000502847521020018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500006119686251001010100001010000502847521020018200372003718446031876710163201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmlt d0, d8, #0
  fcmlt d1, d8, #0
  fcmlt d2, d8, #0
  fcmlt d3, d8, #0
  fcmlt d4, d8, #0
  fcmlt d5, d8, #0
  fcmlt d6, d8, #0
  fcmlt d7, d8, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

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)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)9fa0a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715003929258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100060011151181160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002024720039200392003920039
8020420038150001992680116100800161008002850064019612002820048200499976109986801282008003820080038200492004811802011009910010080000100000022251281231120046800001002005020050200502004920050
802042004815000642680116100800161008002850064019602006920048200489976109986801282008003820080233200492004911802011009910010080000100010022251281231120045800001002004920049200492004920050
80204200491500543106268011610080016100800285006401961200282004820048997699986801282008003820080038200482004811802011009910010080000100000322251281231120046800001002004920049200492004920049
802042004815000844268011610080016100800285006401960200282004820048997699986801282008003820080038200482004811802011009910010080000100000022251281231120045800001002004920050200492004920049
8020420048150012642780116100800161008002850064019602002820048200489976259986801282008003820080038200482004811802011009910010080000100000022251281231120045800001002004920049200492004920049
802042004815000930268011610080016100800285006401960200282004820049997699986801282008003820080038200482004811802011009910010080000100000022251281231120045800001002004920049200492004920049
802042004915000642680116100800161008002850064019612002820048200481001199986801282008003820080038200482004811802011009910010080000100000022251281231120045800001002004920049200492004920049
802042004815001264268011610080016100800285006401961200282004820049997699986801282008003820080038200482004911802011009910010080000100000022251281231120046800001002004920049200492004920050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa8accfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150033925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050200171614152003580000102003920039200392003920039
8002420038150008125800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050200111616132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000012001920038200389996310018800102080000208000020088200381180021109101080000100050200151613162003580000102009920098200892003920039
8002420087150108125800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000101050200141615162003580000102003920039200392003920039
8002420038150003925800101080000108000050640000012001920138200879996310018800102080000208000020038200381180021109101080000100050200161616132003580000102003920039200392003920039
80024200381500123925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050200111615182003580000102003920039200392003920039
8002420038150003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050200131613132003580000102003920039200392003920039
8002420038150093925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050200101616132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050200101611132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050200101616132003580000102003920039200392003920039