Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDL (vector, 4S)

Test 1: uops

Code:

  uaddl v0.4s, v0.4h, v1.4h
  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)03191e3f4e51inst 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
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715196116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150126116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
10042037150077316872510001000100026468002018203720371572318951000100020002037203711100110003073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddl v0.4s, v0.4h, v1.4h
  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)03070a191e3f4e51inst 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)9fa7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371501104561196872510100100100001001000050028476800200182003720037184297187411010020010008200200162003720037111020110099100100100001000001117181161119805100001002003820038200382003820038
1020420037150110061196872510100100100001001000050028476800200182003720037184296187401010020010008200200162003720037111020110099100100100001000001117181161119806100001002003820038200382003820038
10204200371501100611968725101001001000010010000500284768002001820037200371842971874010100200100082002001620037200371110201100991001001000010004531117171161119806100001002003820038200382003820038
10204200371501100103196872510100100100001001000050028476800200182003720037184296187411010020010008200200162003720037111020110099100100100001000001117181161119806100001002003820038200382003820038
1020420037150114061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001002000007102162219791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038
1020420037150000061196872510100114100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090a0b18191e1f3f4e51inst 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
100242003715000000100611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404163419785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006403164419785010000102003820038200382003820038
100242003715000000000821968725100101010012101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006403163419785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404164319785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404164419785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000001006403164319785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404164319785010000102003820038200382003820038
1002420037150000000001051968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006403163419785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284807012001820037200371844431876710010201000020203602003720037111002110910101000010000000006403164419785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404164319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uaddl v0.4s, v1.4h, v0.4h
  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)030b1e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500002511968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715001410611968725101001001000010010000500284768020018200842008518422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150030611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000187101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150100611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715004260611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715003270611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150030611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
1002420037150015611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150001611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uaddl v0.4s, v8.4h, v9.4h
  uaddl v1.4s, v8.4h, v9.4h
  uaddl v2.4s, v8.4h, v9.4h
  uaddl v3.4s, v8.4h, v9.4h
  uaddl v4.4s, v8.4h, v9.4h
  uaddl v5.4s, v8.4h, v9.4h
  uaddl v6.4s, v8.4h, v9.4h
  uaddl v7.4s, v8.4h, v9.4h
  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)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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382009011802011009910010080000100000000511061622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
8020420038150007052580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
8020420038150004011980197103800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815000822580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000400511021622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002024120039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733100488010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815000106525801001008000010080000500640000120019200382003899733999680100202800002001600002003820038118020110099100100800001000000570511021622200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100605020316112003580000102003920039200392003920039
80024200381500639258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001008705020116112003580000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382008810004310018800102080000201600002003820038118002110910108000010010205020116112003580000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
8002420038150003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010011705020116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001008105020116112003580000102003920039200392003920039
80024200381500039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381502291392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001009305020216222003580000102003920039200392003920039