Apple M1 Microarchitecture Research by Dougall Johnson

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

UQRSHL (scalar, S)

Test 1: uops

Code:

  uqrshl 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)030818191e1f3f4e51inst 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)a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220000061254825100010001000398313030183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
100430372300000103254825100010001000398313030183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
10043037230000061254825100010001000398313030183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
1004303722000324061254825100010001000398313030183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
10043037220000061254825100010001000398313030183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
100430372300000128254825100010001000398313030183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
10043037220000061254825100010001000398313030183037303724153289510001000200030373037111001100000002828073116112630100030383038303830383038
100430372200012061254825100010001000398313030183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
10043037220000061254825100010001000398313030183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
10043037230000061254825100010001000398313030183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqrshl 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): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500090612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731303001830037301322826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250001507262954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250001507262954825101001001000010010000500427731313001830037301802826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000003462954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b0f18191e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037224000000061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037224000000061295482510010101000010100005042786720300180300373022828287328767100102010000202000030037300371110021109101010000100006402162229630110000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250030000135295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372240000000822954825100101010000101000050427731303001803003730037282873287671001020101682020000300373003721100211091010100001081837506402162229630010000103003830038300383003830038
10024300372240000000189295482510010101000012100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250000027061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100006402162329630310000103008530086300383003830038
100243003722500000088748295212510010111000011100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqrshl 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): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000006129548251010010010000100100005004277313030090300373003728265032874510100200100002002000030037300371110201100991001001000010000310007101161129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250000008229548251010010010000100100005004277313030126300373003728265032874510100200100002002000030037300371110201100991001001000010000000007101161129706100001003003830038300383003830038
102043003722500000010529548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372240000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372256129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372246129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383013230038
100243003722572629548251001011100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372256129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722540529548251001010100001010000504277313030162300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722534629548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630210000103003830038300383003830038
10024300372256129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372246129548251001010100001010148504277313030018300373003728287328767100102010000202000030037300371110021109101010000100027636402162229630010000103003830038300383003830038
10024300372246129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372256129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqrshl s0, s8, s9
  uqrshl s1, s8, s9
  uqrshl s2, s8, s9
  uqrshl s3, s8, s9
  uqrshl s4, s8, s9
  uqrshl s5, s8, s9
  uqrshl s6, s8, s9
  uqrshl 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)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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500412580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000051103161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973739997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
802042003915002332580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399983039997802222008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
802042003915001712580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000051101161220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500001840258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000502071610102003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000200202019020039999631001980010208000020160000200392003911800211091010800001000502071611132003680000102004020040200402004020040
80024200391500000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005020101610102003680000102004020040200402004020040
800242003915000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100350208161072003680000102004020040200402004020040
800242009015001202842580010108000010800005064082802002020039200399996310019800102080000201601962003920039118002110910108000010005020111613122003680000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502010168102003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050207167102003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050208177102003680000102004020040200402004020040
800242003915000015402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010105020121612122003680000102004020040200402004020040
8002420039149000082258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502010161292003680000102004020040200402004020040