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, 16B)

Test 1: uops

Code:

  sqrshl v0.16b, v0.16b, v1.16b
  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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100001573116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372201032548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshl v0.16b, v0.16b, v1.16b
  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)030b1e3f4e51inst 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)9fa1a6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500662954825101001001000010010000500428244030018300373003728265328745101002001000020020000300373003711102011009910010010000100002138007102161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000129017101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000117007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000069007101171129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000114007101161129928100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000114007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000138007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372251070529539251010012110000126100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000003007401161229742100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000054007101161129634100001003003830038300383003830038

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)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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100064000316222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313103001830037300372828732876710010201000020200003003730037111002110910101000010015364000216222963010000103003830038300383003830038
100243008122506129548251001010100001010000504277313003001830037300372828732876710010201000020200003003730037111002110910101000010011764000216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313103001830037300372828732876710010201000020200003003730037111002110910101000010014764000216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050428274100300183003730037282873287671001020100002020000300373003711100211091010100001004864000216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313003001830037300372828732876710010201000020200003003730037111002110910101000010012364000216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100364000216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100364000216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313003001830037300372828732876710010201000020200003003730037111002110910101000010012364000216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313003001830037300372828732876710010201000020200003003730037111002110910101000010112664000216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqrshl v0.16b, v1.16b, v0.16b
  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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000001806071021611296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000100071011611296340100001003027430038300383003830038
10204300372250000000061295482510100100100321001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000206071011611296340100001003003830038300383003830038
10204300372250000000082295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037411020110099100100100001000000300071011611296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722400000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000004700071011611296340100001003003830038300383003830038
1020430037225000001200612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000002909071011611296340100001003003830038300383003830038
10204302272240000000061295482510100100100241001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000200071011611296340100001003003830038300383003830038
102043003722500000120061295482510100100100001001000050042773130300183003730037282793287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722400000000147295482510100100100001001000050042773130300183003730182282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a7a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295482510010101000010100005042773131830018300373003728287328767100102010000202000030037300371110021109101010000100000132064086162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731318300183003730037282873287671001020100002020000300373003711100211091010100001000000064082162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131830018300373003728287328767100102010000202000030037300371110021109101010000100000132064082162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131830018300373003728287328767100102010000202000030037300371110021109101010000100000135064002162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131830018300373003728287328767100102010000202000030037300371110021109101010000100000135064082162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131830018300373003728287328767100102010000202000030037300371110021109101010000100000138064082162229630010000103003830038300383003830038
100243003722500001206312954825100101010000101000050428017718300183003730037282873287671001020100002020000300373003711100211091010100001000000064082162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131830018300373003728287328767100102010000202000030037300371110021109101010000100000129064082162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131830018300373003728287328767100102010000202000030037300371110022109101010000100000111064082162229630010000103003830038300383003830038
10024300372250000007262954825100101010000101000050427731318300183003730037282873287671001020100002020000300373003711100211091010100001000000066882162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqrshl v0.16b, v8.16b, v9.16b
  sqrshl v1.16b, v8.16b, v9.16b
  sqrshl v2.16b, v8.16b, v9.16b
  sqrshl v3.16b, v8.16b, v9.16b
  sqrshl v4.16b, v8.16b, v9.16b
  sqrshl v5.16b, v8.16b, v9.16b
  sqrshl v6.16b, v8.16b, v9.16b
  sqrshl v7.16b, v8.16b, v9.16b
  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)0308181e1f3a3f51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150000009392580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511021611200360800001002004020040200402004020040
8020420039150000008492580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000414380222100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100010511011611200360800001002004020040200402004020040
802042003915000000622580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000001732580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000001252580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040

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)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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915006752580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000502000161613112003680000102004020040200402004020040
80024200391500402580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001010502000121613132003680000102004020040200402004020040
800242003915007052580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001010502000141614112003680000102004020040200402004020040
80024200391500402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000502000141613112003680000102004020040200402004020040
800242003915001052580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000502000131612132003680000102004020040200402004020040
80024200391500402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000502000131613132003680000102004020040200402004020040
80024200391500612580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000502000141614142003680000102004020040200402004020040
80024200391500842580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000502051131613102003680000102004020040200402004020040
80024200391500402580010108000012800005064000015200202003920039999631001980010208000020160000200392003911800211091010800001000502000131613122003680000102004020040200402004020040
80024200391500612580010108000010800005064000005200202003920039999631001980010208000020160000200392003911800211091010800001000502000131612122003680000102004020040200402004020040