Apple M1 Microarchitecture Research by Dougall Johnson

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

SHRN (2D)

Test 1: uops

Code:

  shrn v0.2s, v0.2d, #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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110003073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110009073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110004073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110002073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  shrn v0.2s, v0.2d, #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)03080918191e1f3f4e51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240000002862295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000000165295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722400000061295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037225000000251295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500000082295472510100104100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000307101161129633100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080918191e1f3a3f4e51inst 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)9fa0a1a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102210000201000030037300371110021109101010000100000786402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010220006402162229787010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010040606402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830084300372828632876710010201000020100003003730037111002110910101000010000066402162229629010000103003830038300383003830038
10024300372240000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402322229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000036402162229629010000103003830038300383003830038
10024300372240000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000001682954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722600000001032954725100101010000101000050427716003009030037300372828632876710010201000020100003003730037111002110910101000010000106402162229629010000103003830038300383003830038
100243003722500000002512954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  shrn v0.2s, v8.2d, #3
  shrn v1.2s, v8.2d, #3
  shrn v2.2s, v8.2d, #3
  shrn v3.2s, v8.2d, #3
  shrn v4.2s, v8.2d, #3
  shrn v5.2s, v8.2d, #3
  shrn v6.2s, v8.2d, #3
  shrn v7.2s, v8.2d, #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)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)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)9fa0a8a9acc2c5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080143200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391501072458030810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016020074800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308091e3f51inst 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)9fa0a1a8accfd2d5d6dbddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100000502001716017620036080000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100000502001716017720036080000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100000502001716017620036080000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100000502001716017620036080000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999960310019800102080000208000020141200901180021109101080000100000502001716061820036080000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100000502008160617200361380000102004020040200402004020040
8002420039150000402580010108000010800005064000012002220039200399996031001980010208000020800002003920039118002110910108000010000050200816081720036080000102004020040200402004020040
80024200391500003852580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050200816017620036080000102004020040200402004020040
80024200391500004572580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000050200816061720036080000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001024018985114010851161920281080000102035120345203492040020352