Apple Microarchitecture Research by Dougall Johnson

M1/A14 P-core (Firestorm): Overview | Base Instructions | SIMD and FP Instructions
M1/A14 E-core (Icestorm):  Overview | Base Instructions | SIMD and FP Instructions

UQSHL (vector, 2D)

Test 1: uops

Code:

  uqshl v0.2d, v0.2d, v1.2d
  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 uop (01)cycle (02)031e1f3f4e51schedule uop (52)schedule simd uop (54)dispatch simd uop (57)ldst uops in schedulers (5b)696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map simd uop (7e)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst simd alu (9a)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)f5f6f7f8fd
100420371600611687251000100010002646802018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl v0.2d, v0.2d, v1.2d
  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 uop (01)cycle (02)031e3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)6061696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)a9acc2branch cond mispred nonspec (c5)cfd0d5map dispatch bubble (d6)ddfetch restart (de)e0eb? simd retires (ee)? int retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680152001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038
1020420037150032919687251010010010000100100005002847680002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680152001820084200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038
102042003715008419687251010010010000100100005002847680102001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680152001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680102001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038
102042003714906119687251010010010000100100005002847680102001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038
1020420037150053619687251010010010000100100005002847680052001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710511611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03mmu table walk data (08)18191e1f3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)l1d tlb miss (a1)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acc2cfd5map dispatch bubble (d6)daddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
100242003715000000275196211331008512100721510912882847680020234203192032118444318767100102010000202000020037200371110021109101010000100000000064021602219785010000102003820038200382003820038
100242003715000079235282196872510010101000010100005028476800200182003720037184443187671001020100002021338203192003771100211091010100001022300212115064021602219785010000102003820038200382003820038
10024200371490000017019676122100241010000131091256285537802023420358203921846032188741108022111672022324203692036771100211091010100001020211013993081127204320091410000102013220370203752041920367
10024203691531772676163914196218010099181008415111516028515290202702037320133184663187671001020100002020000200372003711100211091010100001040201014035280821602220073310000102008520369203702037120417
10024203681530872675283419196651331006216100721410152762854095020162203682008318454718879110762010163202234220229203228110021109101010000100000000064032402219824510000102027620133201782027520321
100242017915105667217682196872510010101000010100006028566610200182003720037184442618787104682410613222219420217203703110021109101010000100020125995070154803220022410000102003820038200382003820038
100242003715000000611967625100101010072101091260285409502001820037200371844431876710010201000020200002003720037111002110910101000010000000006402161072219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021602219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021602219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021602219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uqshl v0.2d, v1.2d, v0.2d
  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 uop (01)cycle (02)03181e3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb miss (a1)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
102042003715006310319687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011621197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200542003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500048319687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500012419687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03mmu table walk instruction (07)mmu table walk data (08)l2 tlb miss instruction (0a)1e3a3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002420037150101926819687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000644101610111978510000102003820038200382003820038
1002420037150101026819687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038
1002420037149101026819687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038
100242003715010102681968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100064410161051978510000102003820038200382003820038
1002420037150101026819687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000644101612101978510000102003820038200382003820038
1002420037150101026819687251001010100001010000502847680200182003720037184443187671016320100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038
10024200371501010273319687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000644111610101978510000102003820038200382003820038
1002420037150101026819687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038
100242003715010102681968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100064410161051978510000102003820038200382003820038
100242003715010102681968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100064410165101978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uqshl v0.2d, v8.2d, v9.2d
  uqshl v1.2d, v8.2d, v9.2d
  uqshl v2.2d, v8.2d, v9.2d
  uqshl v3.2d, v8.2d, v9.2d
  uqshl v4.2d, v8.2d, v9.2d
  uqshl v5.2d, v8.2d, v9.2d
  uqshl v6.2d, v8.2d, v9.2d
  uqshl v7.2d, v8.2d, v9.2d
  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 uop (01)cycle (02)031e3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fld unit uop (a6)l1d cache writeback (a8)acbranch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220016006420038200381180201100991001008000010010011151180161020035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
8020420038150061258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)03mmu table walk instruction (07)l2 tlb miss instruction (0a)3a3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
800242004715011271425800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050241316141420035080000102003920039200392003920039
80024200381501124925800101080000108000050640000020019201882003899963100188001020800002016000020038200381180021109101080000100050241816162020035080000102003920039200392003920039
80024200381501124925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050242016181820035080000102003920039200392003920039
8002420038150112492580010108000010800005064000002001920038200389996310018800102080000201600002019020038118002110910108000010005024131691620035080000102003920039200392003920039
80024200381501124925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100050241616171820035080000102003920039200392003920039
80024200381501124925800101080000108000050640000020019200382003899963100188011020800002016000020038200381180021109101080000100050241616161620035080000102003920039200392003920039
800242008715011249258001010800001080000506400001200192003820038999617100188001020800002016000020038200381180021109101080000100050411316151820035080000102003920039200392003920039
80024200381501124925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100050241516151320035080000102003920039200392003920039
80024200381501124925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100050241816151620035080000102003920039200392003920039
80024200381501124925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050241416181620035080000102003920039200392003920039