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, 2D)

Test 1: uops

Code:

  fcmeq v0.2d, v0.2d, v1.2d
  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)030b1e1f3f4e51inst 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)a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371600061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371500061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371500061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371500082168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371500061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371600061168725100010001000264680120182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371500061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371500061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715015061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq v0.2d, v0.2d, v1.2d
  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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000307101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000253196762510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmeq v0.2d, v1.2d, v0.2d
  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)03080b18191e1f3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500100300611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10205200371500000180611968725101001001000010010000500284768002001820037200841842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000901031968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000623284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231876310269200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231881610100200100002002000020037200371110201100991001001000010000103071011611197910100001002008620086200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000001950071011611197910100001002003820038200382003820038
1020420037150100000611968725101001141001211610152612284768002001820037200371842231874510100200100002002099620037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000100176611967625101001001000010010000500284768002001820037200371842231874510100200100002002066420037200371110201100991001001000010000000075811611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033a3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516551978510000102003820038200382008620038
1002420037150014161968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516541978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516541978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516551978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640416451978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010002640416551978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640416451978510000102003820038200382003820038
10024200371500611968725100101010000101015050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516541978510000102003820038200382003820038
10024200371490611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516451978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640416441978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmeq v0.2d, v8.2d, v9.2d
  fcmeq v1.2d, v8.2d, v9.2d
  fcmeq v2.2d, v8.2d, v9.2d
  fcmeq v3.2d, v8.2d, v9.2d
  fcmeq v4.2d, v8.2d, v9.2d
  fcmeq v5.2d, v8.2d, v9.2d
  fcmeq v6.2d, v8.2d, v9.2d
  fcmeq v7.2d, v8.2d, v9.2d
  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)03080b1e3f51inst 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)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)9fa0a1a6a8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000940258010010080000100800005006400001200190200382003899730399968010020080000200160000200382003811802011009910010080000100000230051103162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000200190200382003899730399968010020080000200160000200382003811802011009910010080000100000030051102162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200190200382003899730399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039
8020420038150000420258010010080000100800005006400001200190200382003899730399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200193200382003899730399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200190200382003899730399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200190200382003899730399968010020080000200160000200382003811802011009910010080000100010000051102162220035800001002003920039200392003920039
8020420038150006402580100100800001008000050064000012001902003820038997303999680100200800002001600002003820038118020110099100100800001000000780051102162220035800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019020038200389973039996801002008000020016000020038200381180201100991001008000010000001020051102162220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200190200382003899730399968010020080000200160000200382003811802011009910010080000100000030051102162220035800001002003920039200392003920039

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)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)9fa7a8a9accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200281626262003580000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010020050200251624252003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200271627282003580000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000350200211613272003580000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050200151627162003580000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050200191625202003580000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050200211627162003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200271628282003580000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010010050200221626162003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200271616272003580000102003920039200392003920039