Apple M1 Microarchitecture Research by Dougall Johnson

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

SHRN (4S)

Test 1: uops

Code:

  shrn v0.4h, v0.4s, #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)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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100005073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383086303830383038
1004303723082254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724961254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  shrn v0.4h, v0.4s, #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)0304070818191e1f3a3f4e51inst 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)9fa6a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722401000210061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
102043003722500000000160295472510100100100001001000050042771600300183003730037282643287451010020010166200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
102043003722500000000509295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730084111020110099100100100001000000071021622296330100001003003830038300853003830038
102043003722500000300191295472510100100100001001000050042771600300183008430037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003013630038300383003830038
10204300372250000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071022622296330100001003003830038300383003830038
10204300372250000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
102043003722500000000212295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003008530086111020110099100100100001000000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3a3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103008630038300383003830086
100243003722510000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010106403163329629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010106403163329629010000103003830038300383003830038
100243003722500000822954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010106403163329629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037225000001472954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  shrn v0.4h, v8.4s, #3
  shrn v1.4h, v8.4s, #3
  shrn v2.4h, v8.4s, #3
  shrn v3.4h, v8.4s, #3
  shrn v4.4h, v8.4s, #3
  shrn v5.4h, v8.4s, #3
  shrn v6.4h, v8.4s, #3
  shrn v7.4h, v8.4s, #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)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)9facc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500302580108100800081008002850064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001511151181620036800001002004020040200402004020040
80204200391500582580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001211151181620036800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010011711151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001211151181620036800001002004020040200402004020040
802042003915036330258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181620036800001002004020040200402004020040
8020420039150630258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181620036800001002004020040200402004020040
802042003915003025801081008000810080108500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010013511151181620036800001002004020040200402004020040
8020420039150067258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100611151181620036800001002004020040200402004020040
8020420039150051258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181620036800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181620036800001002004020040200402004020040

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391510402580010108000010800005064000001200202003920090999631001980010208000020800002003920039118002110910108000010005020151612122003680000102004020040200402004020040
80024200391500402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010005020101611132003680000102004020040200402004020040
80024200391500802580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010005020111612122003680000102004020040200402004020040
800242003915002302580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010005020121613102003680000102004020040200402004020040
80024200391500404780010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010235020111610122003680000102004020040200402004020040
80024200391500402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010035020111610112003680000102004020040200402004020040
80024200391500402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010005020111612112003680000102004020040200402004020040
800242003915004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100050206167112003680000102004020040200402004020040
800242003915004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000104005020121612122003680000102004020040200402004020040
80024200391500402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010211025020131611142003680000102004020040200402004020040