Apple M1 Microarchitecture Research by Dougall Johnson

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

USHL (vector, 16B)

Test 1: uops

Code:

  ushl v0.16b, v0.16b, v1.16b
  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)03080b191e3f4e51inst 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715000361168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715000061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000661168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715000061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  ushl v0.16b, v0.16b, v1.16b
  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)030b18191e1f3f4e51inst 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)9fa0a6a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021611197910100001002003820038200382003820038
10204200371560000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371560000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715500000103196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371550000082196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000009071011611197910100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371550000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000010071011611197910100001002003820038200382003820038

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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000901241968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010003640216221978510000102003820038200382003820038
1002420037161001203551968743100101210000121000050284768012001820037200371844431876710165201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150004470611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000904351968725100101010012111000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150003990611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150003450611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500028806119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006401117122003410000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  ushl v0.16b, v1.16b, v0.16b
  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)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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550166196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037156061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371550263196872510100100100001001000050028476800200182003720085184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037155361196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371550275196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037155061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000710116111979114100001002003820038200382003820038
10204200371550209196872510100100100001001000050028476801200182008420037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371556124196872510100100100001001000050028476801200182003720037184220318765101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715512979196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100001071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308181e3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003716010061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715500066196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000003640216221978510000102003820038200382003820038
10024200371560006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100050114640216221978510000102003820038200862003820038
100242003715500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  ushl v0.16b, v8.16b, v9.16b
  ushl v1.16b, v8.16b, v9.16b
  ushl v2.16b, v8.16b, v9.16b
  ushl v3.16b, v8.16b, v9.16b
  ushl v4.16b, v8.16b, v9.16b
  ushl v5.16b, v8.16b, v9.16b
  ushl v6.16b, v8.16b, v9.16b
  ushl v7.16b, v8.16b, v9.16b
  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)0308090b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815500000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000005110216112003500800001002003920039200392003920039
8020420038155000000001032580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
8020420038155000000001032580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
802042003816000000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000103005110116112003500800001002003920039200392003920039
802042003815500000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392008720039
802042003815500000000822580180100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
802042003815500000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
802042003815500000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
8020420038156000000001032580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000005110116112003500800001002003920039200392003920039
802042003816100000000402580100100800001098000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000005110116122003500800001002003920039200392003920039

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)696d6edispatch 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
8002420048155049925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502015161662003580000102003920039200392003920039
8002420038155018625800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502016166162003580000102003920039200392003920039
80024200381550146258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010005020161616162003580000102003920039200392003920039
80024200381550725258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010005020161615152003580000102003920039200392003920039
8002420038155010625800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502016161662003580000102003920039200392003920039
8002420038155070925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502016166162003580000102003920039200392003920039
80024200381550128325800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502016166162003580000102003920039200392003920039
8002420038155039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010005020161616162003580000102003920039200392003920039
800242003815501652580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100350206161662003580000102003920039200392003920039
800242003815503925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502016166162003580000102003920039200392003920039