Apple M1 Microarchitecture Research by Dougall Johnson

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

UHSUB (vector, 4S)

Test 1: uops

Code:

  uhsub v0.4s, v0.4s, v1.4s
  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)030b1e3f4e51inst 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)a0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
1004203716006116872510001000100026468012018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
1004203715106116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
1004203715008216872510001000100026468012018203720371572318951000100020002037203711100110000030073116111787100020382038203820382038
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000000012673116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uhsub v0.4s, v0.4s, v1.4s
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001002107101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200842003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037149006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001357101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064041644197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064041644197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064041644197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064041643197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000102000000064041644197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064041644197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064041643197850010000102003820038200382003820038
1002420037150000009006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064041643197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064041644197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064041644197850010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uhsub v0.4s, v1.4s, v0.4s
  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)03181e1f3a3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100012171011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000941968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001371011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000821968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)~dispatch ld/st (58)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150019519687251001010100001010000050284768012001820037200371844431876710010201000020203442003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251003610100001010000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221989210000102003820038200382003820038
100242003715006119687251001010100001010000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500103819687251001010100001010000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150042219687251001010100001010000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000050284768012001820037200371844431876710010201000020200002003720037111002210910101000010100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uhsub v0.4s, v8.4s, v9.4s
  uhsub v1.4s, v8.4s, v9.4s
  uhsub v2.4s, v8.4s, v9.4s
  uhsub v3.4s, v8.4s, v9.4s
  uhsub v4.4s, v8.4s, v9.4s
  uhsub v5.4s, v8.4s, v9.4s
  uhsub v6.4s, v8.4s, v9.4s
  uhsub v7.4s, v8.4s, v9.4s
  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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150017025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000051106161120035800001002003920039200392003920039
8020420038187069950801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
8020420038149018325801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
8020420038150020725801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
8020420038150023925801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001002000051101161120035800001002003920039200392003920039
8020420038150020825801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b18191e1f3a3f51inst 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
8002420047150000000001902580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050204164420035080000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050204164520035080000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205165520035080000102003920039200392003920039
8002420038150000000004152580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000100050205164420035080000102003920039200392003920039
8002420038150000000007242580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050204164420035080000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050203163320035080000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050203164420035080000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050203163420035080000102003920039200392003920039
800242003815000000000392580388108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205163520035080000102003920039200392003920039
8002420038150000000001022580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050202164420035080000102003920039200392003920039