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, 8H)

Test 1: uops

Code:

  uaddl v0.8h, 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)03181e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073316221787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715001181687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203716012611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371503611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371500611687251000100010002661882018203720371572318951000100020002037203711100110000073216211787100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddl v0.8h, 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)0308090b18191e1f3a3f4e51inst 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
10204200371500000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000240061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611198460100001002003820038200382003820038
10204200371500000000066196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000060061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000120061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000001500441196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000004470061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa8a9accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715015061196872510010101000010100005028476801112001820037200371844431876710010201000020200002003720037111002110910101000010000640116416221978510000102003820038200382003820038
1002420037150180631196872510010101000010100005028476801112001820037200371844431876710010201000020200002003720037111002110910101000010000640116216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801112001820037200371844431876710010201000020200002003720037111002110910101000010000640116216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801112001820037200371844431876710010201000020200002003720037111002110910101000010000640117216221978510000102008520038200382003820038
10024200371500061196872510010101000010100005028476801112005420037200371844431876710010201000020200002003720037111002110910101000010003640114216221978510000102003820038200382008520038
10024200371501380189196872510010101000010100005028476801112001820037200371844431876710010201000020200002003720037111002110910101000010000640114224221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801112001820037200371844431876710010201000020200002003720037111002110910101000010000640114216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801112001820037200371844431876710010201000020200002003720037111002110910101000010003640114216221978510000102003820038200382003820038
100242003715012061196872510010101000010100005028476801112001820037200371844431876710010201000020200002003720037111002110910101000010000640114216221978510000102003820038200382003820038
1002420037150204061196874410010101000010100005028476801112001820037200371844431876710010201016622200002003720037111002110910101000010111975640117216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uaddl v0.8h, 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
1020420037150606119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715012093519687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150606119676251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371501506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150008219687251010010010008100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000022506119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000101000000064021622197850010000102003820038200382003820038
1002420037150000001206119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110022109101010000100000000064021622197850010000102003820038200382003820038
100242003715000000606119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
1002420037150000009306119687251001010100001010000502848298020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
10024200371500000053406119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uaddl v0.8h, v8.8b, v9.8b
  uaddl v1.8h, v8.8b, v9.8b
  uaddl v2.8h, v8.8b, v9.8b
  uaddl v3.8h, v8.8b, v9.8b
  uaddl v4.8h, v8.8b, v9.8b
  uaddl v5.8h, v8.8b, v9.8b
  uaddl v6.8h, v8.8b, v9.8b
  uaddl v7.8h, 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)030818191e1f3f51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150000180402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051102161120035800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000120402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000270402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000570402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120083800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa0a1a8a9accfd5d6d9ddinst fetch restart (de)e0ebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020316066200350080000102003920039200392003920039
80024200381920033672580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010001005020416034200350080000102003920039200392003920039
80024200381500024392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020416043200350080000102003920039200392003920039
800242003815000060258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005135020416043200350080000102003920039200392003920039
80024200381500021392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020316043200350080000102003920039200392003920039
800242003815000474392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020316055200350080000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020416055200350080000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020316033200350080000102003920039200392003920039
80024200381500012612580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000005020416033200350080000102003920039200392003920039
80024200381500012392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000005020516034200350080000102003920039200392003920039