Apple M1 Microarchitecture Research by Dougall Johnson

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

UMINP (vector, 4H)

Test 1: uops

Code:

  uminp v0.4h, v0.4h, v1.4h
  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)60696d6edispatch 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
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037156611687251000100010002646801201820372037157231895100010002000203720371110011000873216221787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000373216221787100020382038203820382038
10042037160611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037163611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
100420371501461687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  uminp v0.4h, v0.4h, v1.4h
  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)03090b1e1f3a3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200841110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100219671011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03090b1e3f4e51inst 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)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500001261968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640516541978510000102003820038200382003820038
10024200371500001031968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516551978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516551978510000102003820038200382003820038
1002420037150003821968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516551978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516441978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640516541978510000102003820038200382003820038
1002420037166014689801968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516541978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640416551978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640516451978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010010640516451978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uminp v0.4h, v1.4h, v0.4h
  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)0309191e3f4e51inst 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)60696b6d6edispatch 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)9fa8a9cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000061196873610100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150010232196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100027101161119791100001002003820038200382003820038
102042003715000061196872510115100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307191e3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006404165519785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006404165519785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006405165519785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006406164619785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006406166519785010000102003820038200382003820038
100242003715000961196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006405166519785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006405166519785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006405165619785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006405165619785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006406165519785010000102003820038200852003820038

Test 4: throughput

Count: 8

Code:

  uminp v0.4h, v8.4h, v9.4h
  uminp v1.4h, v8.4h, v9.4h
  uminp v2.4h, v8.4h, v9.4h
  uminp v3.4h, v8.4h, v9.4h
  uminp v4.4h, v8.4h, v9.4h
  uminp v5.4h, v8.4h, v9.4h
  uminp v6.4h, v8.4h, v9.4h
  uminp v7.4h, v8.4h, v9.4h
  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)030918191e3f51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000015402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100511031611200350800001002003920039200392003920039
80204200381500000612580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382009111802011009910010080000100511011611200350800001002003920039200392003920039
80204200381501000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011621200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)9fa8accfd0d2icache miss (d3)itlb miss (d4)d5d6d9daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502000001616001182003580000102003920039200392003920039
800242003815080825800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020000018160012142003580000102003920039200392003920039
800242003815070725800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020000015160014152003580000102003920039200392003920039
8002420038150392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502000001116001192003580000102003920039200392003920039
800242003815080425800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020000014160014142003580000102003920039200392003920039
800242003815083925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020000118160012162003580000102003920039200392003920039
80024200381503925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020000010160014102003580000102003920039200392003920039
8002420038150104925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020000011160014152003580000102003920039200392003920039
80024200381503925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020000012160016122003580000102003920039200392003920039
80024200381503925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020000013160011152003580000102003920039200392003920039