Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHRN (8H)

Test 1: uops

Code:

  sqrshrn v0.8b, v0.8h, #3
  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)03080b191e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)6061696d6edispatch 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)a0a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722000006125472510001000100039816000301830373037241432895100010001000303730371110011000000730116112629100030383038303830383038
1004303723000006125472510001000100039816000301830373037241432895100010001000303730371110011000000730116112629100030383038303830383038
1004303723000006125472510001000100039816000301830373037241432895100010001000303730371110011000000730116112629100030383038303830383038
1004303722000006125472510001000100039816010301830373037241432895100010001000303730371110011000000730116112629100030383038303830383038
1004303722000006125472510001000100039816010301830373037241432895100010001000303730371110011000000733116112629100030383038303830383038
10043037220000888225472510001000100039816003301830853037241432895115010001000303730371110011000000950116112629100030383038303830853086
1004303723011006012547251000100010003981600330183073303724143289511501000100030373037211001100020220730116112629100030853085307430383085
1004308424100156070925472510001000100039816003301830373037241432895100010001000303730371110011000003730116112629100030383038303830383038
100430372200012010325472510001000100039816003301830373037241432895100010001000303730371110011000000730116112629100030383038303830383038
1004303722000008225472510001000100039816010301830373037241432895100010001000303730371110011000000730116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshrn v0.8b, v0.8h, #3
  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)030818191e1f3a3f4e51inst 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)9fa0a6a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250000006129547441010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710011611298130100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000003710011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632878810010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
1002430037233000612954725100101010000101000050427716013001830037300372828632876710160201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316132962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
1002430037225009612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010010640316332962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqrshrn v0.8b, v8.8h, #3
  sqrshrn v1.8b, v8.8h, #3
  sqrshrn v2.8b, v8.8h, #3
  sqrshrn v3.8b, v8.8h, #3
  sqrshrn v4.8b, v8.8h, #3
  sqrshrn v5.8b, v8.8h, #3
  sqrshrn v6.8b, v8.8h, #3
  sqrshrn v7.8b, v8.8h, #3
  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)030918191e1f3f51inst 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)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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591502000041025801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
8020420039150000005125801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
8020420039161000003025801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151182160020036800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040

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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010050201816552003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010050204161152003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001005020616572003680000102004020040200402004020040
8002420090151040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010050204165112003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001005020616552003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001005020616532003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010050206165112003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010050205164102003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010050205166112003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001005020516562003680000102004020040200402004020040