Apple M1 Microarchitecture Research by Dougall Johnson

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

URECPE (vector, 4S)

Test 1: uops

Code:

  urecpe v0.4s, v0.4s
  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)03181e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372400611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
1004303723001031900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
1004303723002511900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
1004303723093611900251000100010001044513018303730372738328951000100010003037303711100110001073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372303611900251000100010001044513018303730372738328951000100010003037303711100110000073124112919100030383038303830383038
10043037240132611900251000100010001044513018303730372738328951000100010003037303711100110001073116112919100030383038303830383038

Test 2: Latency 1->2

Code:

  urecpe v0.4s, v0.4s
  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)03040b18191e3a3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233105000611990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010008707101161129919100001003003830038300383003830038
1020430037233001100611990025101001001000010010000500106745103001830037300372858832874510100200100002001000030037300371110201100991001001000010001207101161129919100001003003830038300383003830038
10204300372320000001031990025101001001000010010000500106745103001830037300372858832874510100200100002001000030037300371110201100991001001000010002107101161129919100001003003830038300383003830038
1020430037233000000611990025101001001000010010000500106745103001830037300372858832874510100200100002001000030037300371110201100991001001000010007807101161129919100001003003830038300383003830038
1020430037233000000611990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010002107101161129919100001003003830038300383003830038
1020430037233000000611990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010002107101162029919100001003003830038300383003830038
10204300372320000001171990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010008407101161129919100001003003830038300383003830038
1020430037232000000611990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010002107101161129919100001003003830038300383003830038
1020430037233000000611990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010009907101161129919100001003003830038300383003830038
102043003723200001205811990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010001207101161129919100001003003830038300383003830038

1000 unrolls and 10 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)9fa0a1a6a8acbranch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000000611990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010000103003830038300383003830038
10024300372320000001561990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010000103003830038300383003830038
1002430037233000000611990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010000103003830038300383003830038
1002430037233000000611990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010000103003830038300383003830038
1002430037225000000611990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010000103003830038300383003830038
1002430037225000000611990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010000103003830038300383003830038
10024300372250000001031990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010000103003830038300383003830038
1002430037225000000611990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010002103003830038300383003830038
1002430037225000000611990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010000103003830038300383003830038
1002430037225000000611990025100101010000101000050106745103001830037300372861003287671001020100002010000300373003711100211091010100001000000064002162229919010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  urecpe v0.4s, v8.4s
  urecpe v1.4s, v8.4s
  urecpe v2.4s, v8.4s
  urecpe v3.4s, v8.4s
  urecpe v4.4s, v8.4s
  urecpe v5.4s, v8.4s
  urecpe v6.4s, v8.4s
  urecpe v7.4s, v8.4s
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)030407080b18191e1f3f51inst 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)9fa6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802048004059900000000392580100100800001008000050064000018002008003980039699716699938010020080008200800088003980039118020110099100100800001000000011151172162280036800001008004080040801388004080040
802048003959900000000392580100100800001008000050064000018002008003980039699716699938010020080008200800088003980039118020110099100100800001000000011151172162280036800001008004080040800408004080040
802058003960000000000392580100100800001008000050064000008002008003980039699716699938010020080008200800488003980039118020110099100100800001000000011151171162180036800001008004080040800408004080040
802048003959900000000392580100100800001008000050064000018002008003980039699716699938010020080008200800088003980039118020110099100100800001000000011151172162180036800001008004080040800408004080040
802048003960000000000392580100100800001008000050064000018002008003980039699716699938010020080008200800088003980039118020110099100100800001000000011151172162280036800001008004080040800408004080089
8020480039600000000007042580100100800001008000050064000008002008003980039699716699938010020080008200800088003980039118020110099100100800001000000011151172162280036800001008004080040800408004080040
8020480039600000000007042580100100800001008000050064000008002008003980039699716699938010020080008200800088003980039118020110099100100800001000000011151171162280036800001008004080040800408004080040
802048003960000000000392580100100800001008000050064000008002008003980039699716699938010020080008200800088003980039118020110099100100800001000000011151171162180036800001008004080040800408004080040
802048003960000000000392580100100800001008000050064000008002008003980039699716699938010020080008200800088003980039118020110099100100800001000000011151171162180036800001008004080040800408004080040
802048003960000000000392580100122800001008000050064000008002008003980039699716699938010020080008200800088003980039118020110099100100800001000100011151172162180036800001008004080040800408004080040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)0318191e1f3f51inst 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)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
800248004059900009625800101080000108000050640000800208003980039699860370019800102080000208000080039800391180021109101080000100005020216118003480000108004080040800408004080040
80024800396000000147025800101080000108000050640000800208003980039699860370019800102080000208000080039800391180021109101080000100005020116118003480000108004080040800408004080040
800248003960000005025800101080000108000050640000800208003980039699860370019800102080000208000080039800391180021109101080000100005020116118003480000108004080040800408004080040
800248003959900005025800101080000108000050640000800208003980039699860370058800102080000208000080039800391180021109101080000100005020216118003480000108004080040800408004080040
800248003960000005025800101080000108000050640000800208003980039699860370019800102080000208000080039800391180021109101080000100005020116118003480000108004080040800408004080040
800248003959900005025800101080000108000050640000800208003980039699863370019800102080000208000080039800391180021109101080000100005020116118003480000108004080040800408004080040
800248003960100005025800101080000108000050640000800208003980039699860370019800102080000208000080039800391180021109101080000100005020116118003480000108004080040800408004080040
800248003960000005025800101080000108000050640000800208003980039699860370019800102080000208000080039800391180021109101080000100005020116218003480000108004080040800408004080040
800248003960000005025800101080000108000050640000800208003980039699860370019800102080000208000080039800391180021109101080000101005020116118003480000108004080040800408004080040
800248003960000005025800101080000108000050640000800208003980039699860370019800102080000208000080039800391180021109101080000100005020116118003480000108004080040800408004080040