Apple M1 Microarchitecture Research by Dougall Johnson

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

ADDP (vector, 8B)

Test 1: uops

Code:

  addp 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)033f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420851561168725100010001000264680020182037203715723189510001000200020372037111001100012073116111787100020382038203820382038
10042037166116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  addp 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)0304191e1f3a3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371501039006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720085111020110099100100100001002007101161119791100001002003820038200382003820038
10204200371500015006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000012419687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150003750094319687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000008219687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000107101161119791100001002003820038200382003820038
1020420037150001140072619687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500024006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000399006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161219791100001002003820038200382003820038

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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000001200611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006404163419785010000102003820038200382003820038
10024200371500000000611968762100101510012101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006404163419785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000406906614164419824010000102003820038200382003820038
10024200371500000000821968743100101010000111000050284896302001802003720037184443187671001020100002020000200372003711100211091010100001000000006404164419785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006404163319785010000102003820038200382003820038
10024200371490000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006402163419785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006404164319785110000102003820038202282003820038
100242003715000001200611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000307135244519785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006403163419785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000205106404164419785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  addp 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)031e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001003807101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372008511102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150132888219687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101160119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100067101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000247101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3a3f4e51inst 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
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010030640316331978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010030640316451978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010060640316331978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
100242003715000821968725100221010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000103700640316331978510000102003820038200382003820038
100242003715001611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100270640316331978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  addp v0.8b, v8.8b, v9.8b
  addp v1.8b, v8.8b, v9.8b
  addp v2.8b, v8.8b, v9.8b
  addp v3.8b, v8.8b, v9.8b
  addp v4.8b, v8.8b, v9.8b
  addp v5.8b, v8.8b, v9.8b
  addp v6.8b, v8.8b, v9.8b
  addp 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)0308191e3a3f51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000003511021611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000027511011611200350800001002003920039200392003920039
80204200381500000612580100106800951008000050064000012001902003820038997339996801002008000020016000020038200381180201100991001008000010000081511012811200350800001002003920039200392003920100
8020420038149000040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000010511011611200350800001002003920039200392003920039
80204200381500000610258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500000124258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000003511011611200350800001002003920039200392003920039
8020420038149000082258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000073508511011611200350800001002003920039200392003920039
80204200381501100258258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000003511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500012040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b181e1f3a3f51inst 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)6061696d6edispatch 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)9fa0a1a8a9acc2cfd0d2d5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000009008125800101080000108000050640000152001920038200389996310018800102080000201600002003820038118002110910108000010000072050205011601120035080000102003920039200392003920039
80024200381500000000602580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000050205011601120035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000050205011601120035080000102003920039200392003920039
80024200381500000300392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000100050205011601120035080000102003920039200392003920039
800242003815000005400392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000040050205011601120035080000102003920039200992003920039
80024200381500000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000050205011601120035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000003050205011601120035080000102003920039200392003920039
80024200381630000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000003050205011601220035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100000138050205011601220035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000103050205111601120035080000102003920039200392003920039