Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHRN (H)

Test 1: uops

Code:

  sqrshrn b0, h0, #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)030a1e3f4e51inst 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
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110001073216222629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303722006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037220019825472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303722006125472510001000100039816013018303730372414328951000100010003037303711100110000373216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshrn b0, h0, #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)0308090b181e1f3f4e51inst 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)696b6d6edispatch 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000007101161129633100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000007101161129633100001003003830038300383003830038
10204300372240000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000020007101161129666100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000007101161129633100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300180300373003728264328745101002021000020010000300373003711102011009910010010000100000000007101161129633100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000007101161129633100001003003830038300383003830038
102043003722500000063129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000007101161129633100001003003830038300383003830038
102043003722500000072629547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100040000007101161129633100001003003830038300383003830038
102043003722400000015629547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000007101161129633100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024305102280009111320880658929448213100961210088161165055428932803034230510305142832243289441151122118052610332305133051111110021109101010000104008027760085551052230049310000103055930510305083049930548
10024305082290108101320528650729457205100781510088131150082429068003034230037300372828632876710010201000020100003003730037111002110910101000010000230948083806129955410000103041630417301803051030463
100243046322900089105679252262954725100101010000101000065428797603034230037300372831741289191136826113132211482304623041510110021109101010000102222402491808105884329934410000103046530457305003046530469
100243046022711010911887926044294751911008714100722011200764287976030270303683036828317342888011062241115722104923003730037111002110910101000010000210306402722229629310000103003830177303723036730085
1002430179227100335403526129547251001010100001010000504277160030018300373003728286728767100102010000201000030037300371110021109101010000100203601678828123653229917310000103017930464302733041830274
10024304022271104000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000340006611243229770310000103022730227301793017830371
1002430370227111334082801343295114410028131001612103007142798640300543008530130282937288051060920103362010249301333013331100211091010100001042014281306402242229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000460306402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010002340006402162229667010000103003830038300383003830038
100243003722500011688612954762100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010202272557006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqrshrn b0, h8, #3
  sqrshrn b1, h8, #3
  sqrshrn b2, h8, #3
  sqrshrn b3, h8, #3
  sqrshrn b4, h8, #3
  sqrshrn b5, h8, #3
  sqrshrn b6, h8, #3
  sqrshrn b7, h8, #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)030708090b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039155000000180028325801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040
80204200391500000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040
80204200391500000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040
80204200391500000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040
80204200391500000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040
80204200391500000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040
8020420039150000000010803025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040
80204200391500000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040
80204200391500000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040
80204200391500000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115118001600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a0b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)dfe0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150011000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000050240211671142003680000102004020040200402004020040
8002420039150000000000012325800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000002605024091611742003680000102004020040200402004020040
800242003915000000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024681661042003680000102004020040200402004020040
800242003915000000009004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024010168542003680000102004020040200402004020040
80024200391500000000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100002000502407167842003680000102004020040200402004020040
800242003915000000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005024081671042003680000102004020040200402004020040
80024200391500000000000632580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502609169552003680000102004020040200402004020040
80024200391500000000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100001000502805169452003680000102004020040200402004020040
80024200391500000000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100001000502406167742003680000102004020040200402004020040
800242003915000000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005026061661142003680000102004020040200402004020040