Apple M1 Microarchitecture Research by Dougall Johnson

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

UZP2 (vector, 4H)

Test 1: uops

Code:

  uzp2 v0.4h, 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)03080a0b18191e1f3a3f4e51inst 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)a1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371600000000611687251000100010002646802018203720371572318951000100020002037203711100110000000073216111787100020382038203820382038
100420371600000000611687251000100010002646802018203720371572318951000100020002037203711100110000010073116111787100020382038203820382038
100420371600000000611687251000100010002646802018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371600000000611687251000100010002646802018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
1004203716000001200611687251000100010002646802018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371600000000611687251000100010002646802018203720371572318951000100020002037203711100110000010073116111787100020382038203820382038
100420371500000000611687251000100010002646802018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371600000000951687251000100010002646802018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371600000000611687251000100010002646802018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371500000000611687251000100010002646802018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uzp2 v0.4h, 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)03070b18191e1f3f4e51inst 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
102042003715510000016819687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371550000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371550000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000100071021622197910100001002003820038200382003820038
10204200371560000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000471021622197910100001002003820038200382003820038
10204200371550000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037155000000187819621100101801321004812810456650285152902009020182201781843116187991049220010332208209922017920133311020110099100100100001004221259330777324321989718100001002008520180201812003820038
10204201701570131010861196874310100130100241161045653728515290200182008420133184331818745104352101033120021006201822003741102011009910010010000100022121908271021623198950100001002003820133200382003820038
102042008615600022732646119687811015412210012137104565562848963020126201332003718425318760104202041005720020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
102042003716200404533526119687251010010010000121100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371550000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b181e1f3f4e51inst 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)9fa0a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715001006119687451001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150000072619687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150000053619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uzp2 v0.4h, 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)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)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550611968725101001001000010010000500284768002001802003720037184223187451074120010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
10204200371556611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000371001161119791100001002003820038200382003820038
102042003715618611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
10204200371556611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715542611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
1020420037155422511968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
10204200371559611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
1020420037155312611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
1020420037155210611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001001071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090a0b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242032115811107810567040497319687251001010100001010000502847680120018200372003718444318767100102010491202131420179202274110021109101010000100430411813007683643220030310000102035820368204072041720227
100242046015811018892470412583195991531004914101121611064602852812120306202252037018460311878610471201016320200002003720037111002110910101000010000000206623483220004110000102008520229203242013420038
100242003716000000072001591968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000003006402161219785010000102003820038200382003820038
10024200371610001003000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371550000007200611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715500000012600611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371550000007800611968725100101010000101000050284768012004020037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371560001102100611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371560000004800611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402163219785010000102003820038200382003820038
1002420037155000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uzp2 v0.4h, v8.4h, v9.4h
  uzp2 v1.4h, v8.4h, v9.4h
  uzp2 v2.4h, v8.4h, v9.4h
  uzp2 v3.4h, v8.4h, v9.4h
  uzp2 v4.4h, v8.4h, v9.4h
  uzp2 v5.4h, v8.4h, v9.4h
  uzp2 v6.4h, v8.4h, v9.4h
  uzp2 v7.4h, 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)03080b18191e1f3f51inst 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
80204200591550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511021611200350800001002003920039200392003920039
8020420038155012190402580100100800001058000050064000002007420038200381000731002280100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000001003511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815600000011925801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200882003899733101038010020080000200160000200382003811802011009910010080000100000004700511011611200350800001002003920039200392003920039
802042003815500000040258010010080000100800005006430760200192003820038997339996801002008000020016000020038200381180201100991001008000010000000300511011611200350800001002003920039200392003920039
802042003815500000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000152511021611200350800001002003920039200392003920039
80204200381561000004025801001008000010080000500640000020019200382003899733999680100202801922001601982008620038218020110099100100800001000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 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)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)9fa8accfd2d5d6d9daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048155936625800101080000108000050640000112001920038200389996310018800102080000201600002003820038118002110910108000010005020031600112003580000102003920039200392003920039
800242003815503925800101080000108000050640000112001920038200389996310018800102080000201600002003820038118002110910108000010005020011600112003580000102003920039200392003920039
800242003815533925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020013800112003580000102003920039200392003920039
800242003815503925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010035020011600112003580000102003920039200392003920039
800242003815503925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020021600222003580000102003920039200392003920039
8002420038156032425800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020011600112003580000102003920039200392003920039
800242003815603925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020011600112003580000102003920039200392003920039
800242003815603925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020011600112003580000102003920039200392003920039
800242003815503925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020011600112003580000102003920039200392003920039
800242003815503925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020011600112003580000102003920039200392003920039