Apple M1 Microarchitecture Research by Dougall Johnson

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

SQABS (vector, 4H)

Test 1: uops

Code:

  sqabs v0.4h, v0.4h
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000116310003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372268425472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722025125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723014725472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqabs v0.4h, 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): 3.0037

retire (01)cycle (02)030b181e3a3f4e51inst 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)9fa0a8acbranch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000612954725101001001000010010000500427716019300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716010300543003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710911611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716009300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710911611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716010300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710911611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307090a0b18191e1f3f4e5051inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000006129547025100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225100000006129547025100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000070629547025100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037224000000006129547025100101010000101000050427716003001830037302142828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000006129547025100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006422163429631010000103003830038300383003830038
1002430037225000000006129547025100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000006129547025100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037224100000006129547025100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006422162229629010000103003830038300383003830038
1002430037225000000006129547025100101010000101000050427716003001830215300372828632876710012201000020100003003730037111002110910101000010000000006401162229629010000103003830038300383003830038
1002430037225000000006129547025100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa0a8a9acc2c5branch mispredict (cb)cdcfd6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160020115800001002004020040200402004020040
8020420039150007225801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100010001115118160020112800001002004020040200402004020040
8020420039150003025801081008000810080020500640132200202024120039997769990801202008003220080032200392003911802011009910010080000100070301115118160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100050013801115118160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100030001115118160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010004307501115118160020036800001002004020040200402004020040
80204200391500030101801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100041015301115118370020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100046015901115118160020036800001002004020040200402004020040
802042003915000125258010810080008100801165006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000340001115118160020036800001002004020040200402004020040
80204200391500029325801081008000810080020511640972200202003920039997769990801202008003220080140200392003911802011009910010080000100041261801115118160020036800001002009020040201132009020040

1000 unrolls and 10 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)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)9fa8accdcficache miss (d3)d5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150040258001010800001080419506400001200202003920039999631001980010208000020800002003920039118002110910108000010100502001160112003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000103530502001160112003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020047200399996310019800102080000208000020039200391180021109101080000101120502001160112008380000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000502001160112003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010100502001160112003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001001530502001160112003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010190502001160112003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010100502001160112003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000104600502001160112003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000502001160112003680000102004020090200402004020040