Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (scalar, S)

Test 1: uops

Code:

  uqshl s0, s0, s1
  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)a8acc2cficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038
10042037160133168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038
100420371915361168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038
1004203715082168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000730116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl s0, s0, s1
  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)0308090e1e3f4e51inst 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)9fa0a1a6a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500024561196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000061196872510115100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000036611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000001710116111979117100001002003820038200382003820038
10204200371500001261196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000018726196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842531874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500002161196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500001261196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371501261196872510010101000010100005028476800200182003720037184441518767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150216119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318842100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150246119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uqshl s0, s1, s0
  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)030a1e3f4e51inst 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)9fa7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100054307102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000307102162219791100001002003820038200382003820038
102042003715000615196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000010207102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000027102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200852003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
1020420037150001031968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001007102162219791100001002003820038200382003820038
1020420037150007681968725101001221000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010004307102162219791100001002003820038200382003820038
102042003715000821968725101001001000010010456500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000015607102162219791100001002003820038200382003820038

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)6061696d6edispatch 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000000064003162219785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680012001820037200371844431876710010201000020200002003720037111002110910101000010000000064012162219785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680002001820037200371844431880410010201000020200002003720037111002110910101000010000000464012162219785010000102003820038200382003820038
100242003715000000030006119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010000000064002162219785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000000064002162219785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000000064012162219785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010000000064012162219785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010000000064002162219785010000102003820038200382003820038
10024200371500000000006119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010000000064002162219785010000102003820038200382003820038
100242003715000000015006119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010000000064012162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uqshl s0, s8, s9
  uqshl s1, s8, s9
  uqshl s2, s8, s9
  uqshl s3, s8, s9
  uqshl s4, s8, s9
  uqshl s5, s8, s9
  uqshl s6, s8, s9
  uqshl s7, s8, s9
  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)03080b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000030030000511031611200350800001002003920039200392003920039
802042003815000000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000008030000511011611200350800001002003920039200392003920039
802042003815000000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000002101410000511011611200350800001002003920039200392003920039
802042003815000000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000005701680000511011611200350800001002003920039200392003920039
80204200381500000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000001200000511011611200350800001002003920039200392003920039
802042003815000000004025801001008000010080000500640000120019200382018999733999680100200800002001600002003820038118020110099100100800001000000000000511011611200350800001002003920039200392003920039
802042003815000000007052580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000700450000511011611200350800001002003920039200392003920039
802042003815000000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000030000511011611200350800001002003920039200392003920039
80204200381500000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000170900000511011611200350800001002003920039200392003920039
802042003815000000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa7a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915002442580010128000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001003605024000191600016162003580000102003920039200392003920039
80024200381506244258001012800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100035024000161600016162003580000102003920039200392003920039
800242003815002519258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005024000181600016162003580000102003920039200392003920039
80024200381500244258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005024000161600016192003580000102003920039200392003920039
800242003815012265258001010800001080000506400001120019200382003899963100188001020800002016000020038200381180021109101080000101305024000131600012152003580000102003920039200392003920039
80024200381500244258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005024000161600016162003580000102003920039200392003920039
8002420038150026525800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010001850240008160008162003580000102003920039200392003920039
80024200381500244258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005024000151600016172003580000102003920039200392003920039
800242003815002442580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000455024000161600016162003580000102003920039200392003920039
80024200381500244258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100005024000161600014162003580000102003920039200392003920039