Apple M1 Microarchitecture Research by Dougall Johnson

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

UMAXP (vector, 4S)

Test 1: uops

Code:

  umaxp 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)03080b191e1f3f4e51inst 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
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715000006116872510001000100026468012018203720371572318951000100020002037203711100110000373116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  umaxp 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)031e3f4e51inst 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)9fa0a1a8cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715024611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
1020420037155426611968725101001001000010010000511284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
1020420037150132611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010020071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307191e3f4e51inst 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)9fa0a1accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000156119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000102206402162219785210000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820085200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500036119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  umaxp 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)0308091e1f3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150009061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100006071011611197910100001002003820038200382003820038
102042003715000180536196872510100100100001001000050028476800200180200372003718439318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150003061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500012061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000660611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006404163419785010000102003820038200382003820038
100242003715000000150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006404163419785010000102003820038200382003820038
100242003715000000420611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404163419785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404163219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404163419785010000102003820038200382003820038
10024200371500000030611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006403164419785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006403164319785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404164319785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006403164419785010000102003820038200382003820038
100242003715000000150611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006404164419785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  umaxp v0.4s, v8.4s, v9.4s
  umaxp v1.4s, v8.4s, v9.4s
  umaxp v2.4s, v8.4s, v9.4s
  umaxp v3.4s, v8.4s, v9.4s
  umaxp v4.4s, v8.4s, v9.4s
  umaxp v5.4s, v8.4s, v9.4s
  umaxp v6.4s, v8.4s, v9.4s
  umaxp 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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103162220035800001002003920039200392003920039
80204200381500000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381500000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002024020039200392003920039
80204200381500001478840258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
802042003815010000402580100100800001008000050064000012001920038200389973310049801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381500000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381500000040258010010080000100800005006400001200192003820038997339996801002008000020016000020140200381180201100991001008000010000051102163220035800001002003920039200392003920039
80204201411500000067825801001008000010080000500640000120019200382003899733100808010020080000200160000200382003811802011009910010080000100118051102162220035800001002003920039200392003920039
802042003815000012040258010010080000100800005006400001200672003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
802042003815000021040258010010080000100800005006400000200192003820038997339996801002008019420016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f3f51inst 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)9fa0a1a8acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015000000392580010108000010800005064000010200192003820038999631001880010208000020160000200382003811800211091010800001000000502052316332003580000102003920039200392003920039
800242003815000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000502054516552003580000102003920039200392003920039
800242003815000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000502054316442003580000102003920039200392003920039
800242003815000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000502054416442003580000102003920039200392003920039
8002420038150000150392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000502054416442003580000102003920039200392003920039
800242003815000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000502054516542003580000102003920039200392003920039
800242003815000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000502054516552003580000102003920039200392003920039
800242003815000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000502054316552003580000102003920039200392003920039
800242003815000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000502054416432003580000102003920039200392003920039
800242003815000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000000502054316342003580000102003920039200392003920039