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, 8B)

Test 1: uops

Code:

  uzp2 v0.8b, 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)031e3f4e51inst 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
10042037160821687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371601071687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160841687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371612611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371501031687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uzp2 v0.8b, 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)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)9fa0a8accfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715572611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371560611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371556611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371556611968725101001001000010010000500284849402001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550611968725101341251000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
102042003715521611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371560611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038
10204200371556611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
10204200371559611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371560611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150002102541968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010669216221978510000102003820038200382003820038
1002420037150006120611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
1002420037150002700611968743100101310000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uzp2 v0.8b, 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)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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715606119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100005371011611197910100001002003820038200382003820038
102042003715512611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000012971011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715608919687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000371011611197910100001002003820038200382003820038
1020420037155025119687251010010010000100100005002847680020018200782003718422318745101002001000020020000200372003711102011009910010010000100001071011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100001071011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000371011611197910100001002003820038200402003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100002371011611197910100001002003820038200382003820038
1020420037155082196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000043071011611197910100001002003820038200382003820038

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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155001861196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006429168219785210000102003820038200382003820038
1002420037156001561196872510010101000010100005028476800200182003720037184443187671001220100002020000200372003711100211091010100001000000006424168419787210000102003820038200382003820038
100242003715600061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003721100211091010100001000000006402162219785210000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200182003720037184443187671001220100002020000200372003711100211091010100001000000006402162219785210000102003820038200382003820038
100242003715500061196872510010101000012100006028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006422162219785010000102003820038200382003820038
100242003715500061196872510012101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715500061196872510010101000010100006028476800200182003720037184443187671001220100002020000200372003711100211091010100001000010006402162119785010000102003820038200382003820038
100242003715600061196872510010101000010100005028476800200182003720037184443187671001220100002020000200372003711100211091010100001000000006402164419785010000102003820038200382003820038
100242003715600089196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uzp2 v0.8b, v8.8b, v9.8b
  uzp2 v1.8b, v8.8b, v9.8b
  uzp2 v2.8b, v8.8b, v9.8b
  uzp2 v3.8b, v8.8b, v9.8b
  uzp2 v4.8b, v8.8b, v9.8b
  uzp2 v5.8b, v8.8b, v9.8b
  uzp2 v6.8b, v8.8b, v9.8b
  uzp2 v7.8b, 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)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)696b6d6edispatch 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)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815500000040258010010080000100800005006400002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000005110216112003500800001002003920039200392003920039
802042003815500000040258010010080000100800005006400002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000005110116112003500800001002003920039200392003920039
802042003815600000040258010010080000100800005006400002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000005110116112003500800001002003920039200392003920039
802042003815500000082258010010080000100800005006400002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000005110116112003500800001002003920039200392003920039
802042003815500000040258010010080000100800005006400002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000005110116112003500800001002003920039200392003920039
802042003815600000040258010010080000100800005006400002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000005110116112003500800001002003920039200392003920039
802042003815500000040258010010080000100800005006400002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000005110116112003500800001002003920039200392003920039
8020420038155000000632580100100800001008000050064000020019020038200389973399968010020080000200160000200382003811802011009910010080000100040101205110116112003500800001002003920039200392003920039
802042003815500000040258010010080000100800005006400002001902003820038997339996801002008000020016000020038200381180201100991001008000010000040005110116112003500800001002003920039200392003920039
8020420038161000012040258010010080000100800005006400002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000005110116112003500800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa6a8accfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420040155003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020019161662003580000102003920039200392003920039
800242003815500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010043502006161662003580000102003920039200392003920039
80024200381551039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050201151616112003580000102003920039200392003920039
80024200381550060925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020015161452003580000102003920039200392003920039
800242003815600392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502006166162003580000102003920039200392003920039
800242003815500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502006161662003580000102003920039200392003920039
8002420038155003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020016166162003580000102003920039200392003920039
80024200381550039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050200161614142003580000102003920039200392003920039
800242003815501222925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100505020013161662003580000102003920039200392003920039
80024200381560039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001001050200161616162003580000102003920039200392003920039