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

SQSHL (vector, 2D)

Test 1: uops

Code:

  sqshl 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)03mmu table walk instruction (07)mmu table walk data (08)l2 tlb miss data (0b)18191e1f3a3f4e51schedule uop (52)schedule simd uop (54)dispatch simd uop (57)ldst uops in schedulers (5b)60696d6emap 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 tlb miss (a1)l1d cache writeback (a8)a9accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)f5f6f7f8fd
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073316221787100020382038203820382038
1004203715000000003131687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371600000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371500000900611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371500000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl 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)60696b6d6emap 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)a9accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715001701968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101163219879100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001802008420037184223187451010020010000200200002003720037111020110099100100100001002207101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371490611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284896312001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03mmu table walk instruction (07)l2 tlb miss instruction (0a)l2 tlb miss data (0b)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)60696d6emap stall dispatch (70)simd prf full (72)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)l1d cache writeback (a8)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002420037150110026819687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010006441016121219785010000102003820038200382003820038
10024200371501100268196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100064481651019785010000102003820038200382003820038
100242003715011032104319687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010006441016121019785010000102003820038200382003820038
1002420037150110026819687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010006441016101019785010000102003820038200382003820038
1002420037150110026819687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010006441216101119785010000102003820038200382003820038
1002420037150110026819687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010006441216101019794010000102003820038200382003820038
100242003715011002681968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000644111651019785010000102003820038200382003820038
10024200371501100211019687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010016441016101019785010000102003820038200382003820038
10024200371501100211019687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010016441116101019785010000102003820038200382003820038
1002420037150110921101968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001040644101610519785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sqshl 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)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)60696b6d6emap 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)st unit uop (a7)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
10204200371501566119687251010010010000100100005002847680120018020037200371842971874110100200100082002001620037200371110201100991001001000010000001117170160019801100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018020037200371842961874110100200100082002001620037200371110201100991001001000010000001117170160019802100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
1020420037150044119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020085200371842331874510100200100002002000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
1020420037150396119687251010010010000100100005002847680120018320037200371842231874510100200100002002000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
1020420037150126119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
1020420037150666119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000000007101164119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03mmu table walk data (08)0f1e3f4e51schedule 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? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002420037150001261196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500015961196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000155361968725100101010000101000050284768002001820037200371844427187671001020100002020000200372003711100211091010100001000640216221992910000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182013120085184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500036061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003714901131861196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500040561196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150001561196872510010101000010100005028476800200182003720037184473187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150002761196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sqshl v0.2d, v8.2d, v9.2d
  sqshl v1.2d, v8.2d, v9.2d
  sqshl v2.2d, v8.2d, v9.2d
  sqshl v3.2d, v8.2d, v9.2d
  sqshl v4.2d, v8.2d, v9.2d
  sqshl v5.2d, v8.2d, v9.2d
  sqshl v6.2d, v8.2d, v9.2d
  sqshl 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)0309l2 tlb miss data (0b)18191e1f3f51schedule 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)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
802042006015000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000516025111200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038150000015040258010010080000100800005006407640200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038150000000103258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038150000000151258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038150000000705258040210080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420190150000012040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000090511011611200350800001002003920039200392003920039
8020420038150000000103258010010080000100800005006400000200192003820038997339996801002008000020016000020038200384180201100991001008000010000202000511011611200740800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)03l2 tlb miss data (0b)18191e1f3f51schedule 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)5f60696d6emap 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)9fcfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
8002420039150000339039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039
80024200381500000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039
80024200381500000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039
80024200381500000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039
80024200381500000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039
80024200381500000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039
80024200381500000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039
80024200381500000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039
80024200381500000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039
80024200381500006039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000105020116112003580000102003920039200392003920039