Apple M1 Microarchitecture Research by Dougall Johnson

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

UMINP (vector, 2S)

Test 1: uops

Code:

  uminp v0.2s, v0.2s, v1.2s
  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)03081e3f4e51inst 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
1004203716006116872510001000100026468002018203720371572318951000100020002037203711100110002073316221787100020382038203820382038
10042037160010316872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150126116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000673216221787100020382038203820382038
1004203715066116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  uminp v0.2s, v0.2s, v1.2s
  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)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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150294061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150573061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200900200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820228200382003820038
100242003715000001031968725100101010000101000050284768002001820037202271844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024202251500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010100640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221992910000102003820038200382003820038
100242003715000120611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444171876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150003176611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010106640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710470201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uminp v0.2s, v1.2s, v0.2s
  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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010052460057101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010049037101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010053007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000037101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000787101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000037101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000877101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3f4e51inst 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
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010030640216221978510000102003820038200382003820038
1002420037149000611968725100101010000101000050284768002001820037200371844431878510010201000020200002003720037111002110910101000010000661216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382008520038
10024200371500021611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010030640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000106130640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010002640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000107400640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uminp v0.2s, v8.2s, v9.2s
  uminp v1.2s, v8.2s, v9.2s
  uminp v2.2s, v8.2s, v9.2s
  uminp v3.2s, v8.2s, v9.2s
  uminp v4.2s, v8.2s, v9.2s
  uminp v5.2s, v8.2s, v9.2s
  uminp v6.2s, v8.2s, v9.2s
  uminp v7.2s, v8.2s, v9.2s
  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)033a3f51inst 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)72scheduler 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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915002262580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010051103162120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973039996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973039996801002008000020016000020038200381180201100991001008000010051101162120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973039996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973039996801002008000020016000020038200381180201100991001008000010051101162120035800001002003920039200392003920039
802042003815001032580100100800001008000050064000002001920038200389973039996801002008000020016000020038200381180201100991001008000010051101162120035800001002003920039200392003920039
80204200381500402580100100800001008000061564000002001920038200389973039996801002008000020016000020038200381180201100991001008000010051101162120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500632580100100800001008000050064000002001920038200389973039996801002008000020016000020038200381180201100991001008000010051101161120035800001002008720039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090a0b18191e1f3a3f51inst 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
80024200471500000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050202162220035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050202162220035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050202162220035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050202162320035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050202162220035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000050202162320035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000103050202162220035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000050202162220035080000102003920039200392003920039
800242003815000000000010225800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000050202162220035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050202162220035080000102003920039200392003920039