Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHL (vector, 8H)

Test 1: uops

Code:

  sqrshl v0.8h, v0.8h, v1.8h
  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)0318191e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000012625482510001000100039831330183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
100430372300006125482510001000100039831330183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
100430372300006125482510001000100039831330183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
100430372300306125482510001000100039831330183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
100430372300006125482510001000100039831330183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
1004303723000012425482510001000100039831330183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
100430372200006125482510001000100039831330183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
100430372300006125482510001000100039831330183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038
100430372200006125482510001000100039831330183037303724153289510001000200030373037211001100000000073116112630100030383038303830383038
100430372300008225482510001000100039831330183037303724153289510001000200030373037111001100000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshl v0.8h, v0.8h, v1.8h
  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)0318191e3f4e51inst 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)9fa1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000612954825101001001000010010000500427731303001830037300372827272874010100200100082002001630037300371110201100991001001000010000011171811611296470100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372827272874010100200100082002001630037300371110201100991001001000010000011171811611296470100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372827272874110100200100082002001630037300371110201100991001001000010000011171711611296470100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372827272874110100200100082002001630037300371110201100991001001000010000011171811611296460100001003003830038300383003830038
1020430037225010612954825101001001000010010000500427731303001830037300372827272874010100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030079300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225315612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722501032954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722539612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722545612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722527612954825100101010000101000050427731313001830037300372828732876710010201000020200003008430037111002110910101000010006402162229630010000103003830038300383003830038
100243003722530612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372259612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722563612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722502512954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqrshl v0.8h, v1.8h, v0.8h
  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)03181e3a3f4e51inst 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)9fa0accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100097101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010001807101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000847101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000787101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000547101161129634100001003003830038300383003830038
1020430037224000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100067101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100037101161029634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010001477101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010001897101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100067101161129634100001003003830038300383003830038

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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372240000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500000007262954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722400000001562954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000028406402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqrshl v0.8h, v8.8h, v9.8h
  sqrshl v1.8h, v8.8h, v9.8h
  sqrshl v2.8h, v8.8h, v9.8h
  sqrshl v3.8h, v8.8h, v9.8h
  sqrshl v4.8h, v8.8h, v9.8h
  sqrshl v5.8h, v8.8h, v9.8h
  sqrshl v6.8h, v8.8h, v9.8h
  sqrshl v7.8h, v8.8h, v9.8h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102161120036800001002004020040200402004020040
8020420039150002312580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915018132412580100100800001008000050064245612002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150270412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150007062580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000008151101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308181e1f3f5051inst 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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000004020023258001010800001080000506400000020020200392003999960310019800102080000201600002003920039118002110910108000010003502031622200360080000102004020040200402004020040
8002420039150000040200232580010108000010800005064000000200202003920039999603100198001020800002016000020039200391180021109101080000100005020416232003603480000102004020040200402004020040
8002420039150009040025800101080000108000050640000012002020039200399996031001980010208000020160000200392003911800211091010800001000123502021622200360080000102004020040200402004020040
80024200391500000400258001010800001080000506400000120020200392003999960310019800102080000201600002003920039118002110910108000010000502021624200360080000102004020040200402004020040
80024200391500000400258001010800001080000506400000120020200392003999960310019800102080000201600002003920039118002110910108000010000502041622200360080000102004020040200402004020040
80024200391500000400258001010800001080000506400000120020200392003999960310019800102080000201600002003920039118002110910108000010000502021622200360080000102004020040200402004020040
80024200391500000400258001010800001080000506400000120020200392003999967310019800102080000201600002003920039118002110910108000010000502041622200360080000102004020040200402004020040
80024200391500000400258001010800001080000506400000120020200392003999960310019800102080000201600002003920039118002110910108000010003502021622200360080000102004020040200402004020040
80024200391500000400258001010800001080000506400000120020200392003999960310019800102080000201600002003920039118002110910108000010000502021644200360080000102004020040200402004020040
80024200391500000400258001010800001080000506400000120020200392003999960310019800102080000201600002003920039118002110910108000010006502021622200360080000102004020040200402004020040