Apple M1 Microarchitecture Research by Dougall Johnson

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

SUB (vector, 8B)

Test 1: uops

Code:

  sub 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)03070a1e3a3f4e51inst 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037151124271168725100010001000264680120182037203715723189510001000200020372037111001100077416441787100020382038203820382038
1004203716110271168725100010001000264680020182037203715723189510001000200020372037111001100077416441787100020382038203820382038
1004203715110271168725100010001000264680020182037203715723189510001000200020372037111001100077416441787100020382038203820382038
1004203715119299168725100010001000264680020182037203715723189510001000200020372037111001100077416441787100020382038203820382038
1004203715110271168725100010001000264680020182037203715723189510001000200020372037111001100077416441787100020382038203820382038
1004203715110271168725100010001000264680020182037203715723189510001000200020372037111001100077416441787100020382038203820382038
100420371511021004168725100010001000264680020182037203715723189510001000200020372037111001100077416441787100020382038203820382038
1004203715110271168725100010001000264680020182037203715723189510001000200020372037111001100077416441787100020382038203820382038
1004203715110271168725100010001000264680020182037203715723189510001000200020372037111001100077416441787100020382038203820382038
1004203715110271168725100010001000264680120182037203715723189510001000200020372037111001100077416441787100020382038203820382038

Test 2: Latency 1->2

Code:

  sub 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): 2.0037

retire (01)cycle (02)0308191e3f4e51inst 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)9facbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038
102042003715000198611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038
10204200371500024611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038
10204200371500027611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979100100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)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)9fa0accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000536196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000661196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000661196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002520037150001861196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sub 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): 2.0037

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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150089196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001001007102162219791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
10204200371500670196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037155061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000307102162219791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150082196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001002007102162219791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
10204200371501261196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03070a1e3a3f4e51inst 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
100242003715011022391968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000644516101019785010000102003820038200382003820038
100242003715011926819687251001011100001010000502847680020018020037200371844431878610164201000020200002003720037111002110910101000010006441016101119785010000102003820038200382003820038
1002420037150110211019676251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006441016111119785010000102003820038200382003820038
1002420037150111226819687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006441016101019785010000102003820038200382003820038
100242003715011182681968725100101010000101000050284768002001802003720037184443187671001020100002020000200852003711100211091010100001000644816101019785010000102003820038200382003820038
1002420037156111562681968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000644101611519785010000102003820038200382003820038
1002420037155110211019687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006441016101019785010000102003820038200382003820038
100242003715011026819687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006441016111019785010000102003820038200382003820038
100242003715011026819687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006441016111119785010000102003820038200382003820038
10024200371501102681968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000644101651019785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sub v0.8b, v8.8b, v9.8b
  sub v1.8b, v8.8b, v9.8b
  sub v2.8b, v8.8b, v9.8b
  sub v3.8b, v8.8b, v9.8b
  sub v4.8b, v8.8b, v9.8b
  sub v5.8b, v8.8b, v9.8b
  sub v6.8b, v8.8b, v9.8b
  sub 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)030708090b18191e1f3f51inst 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)9fa0a1a3a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000700511051611200350800001002003920039200392003920039
80204200381500000000045258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000030511011611200350800001002003920039200392003920039
80204200381500000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000030511013711200350800001002003920039200392003920039
80204200381500000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000060511011611200350800001002003920039200392003920039
802042003815000004012040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000030511011611200350800001002003920039200392003920039
802042003815000000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000540511011610200350800001002003920039200392003920039
80204200381500000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
80204200381500000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
802042003815000000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000002400511011611200350800001002003920039200392003920039
80204200381500000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000130511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03073f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100035020416442003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100035020316342003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000101005020616662003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000102005020916432003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000101005020316342003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020616642003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000103501025020616442003580000102003920039200392003920039
800242003815002292580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000101205020416442003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020416642003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100095020816452003580000102003920039200392003920039