Apple M1 Microarchitecture Research by Dougall Johnson

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

SRSHL (vector, 2S)

Test 1: uops

Code:

  srshl v0.2s, v0.2s, v1.2s
  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
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230822548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  srshl v0.2s, v0.2s, v1.2s
  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)03080b18191e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000096129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250000025129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250000216129548251010010010000100100005004277313300183003730037282653287451010020010000200200003008530084111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000096129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001001007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250000156129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250000126129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

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)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
100243003722400000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830085300383003830038
10024300372250000108061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000036061295482510010101000010100005042773130300183003730085282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000033061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000033061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500003930726295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500004110726295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500003635261295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000102061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  srshl v0.2s, v1.2s, v0.2s
  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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225029761295482510100100100001001000050042773131300183008530037282653287451010020010000200200003003730037111020110099100100100001000007101161029634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003008430037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200203483003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e1f3f4e51inst 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)9fa8cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225060061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225027061295482510010101000010100005042773131300183003730037282873287671015920100002020344300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225024061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300853008511100211091010100001000640216222963010000103003830038300383003830038
1002430037224027061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225057061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300602251426061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250635261295482510010101000010100005042773130300183003730037282873287671001020100002020000300843003711100211091010100001010640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  srshl v0.2s, v8.2s, v9.2s
  srshl v1.2s, v8.2s, v9.2s
  srshl v2.2s, v8.2s, v9.2s
  srshl v3.2s, v8.2s, v9.2s
  srshl v4.2s, v8.2s, v9.2s
  srshl v5.2s, v8.2s, v9.2s
  srshl v6.2s, v8.2s, v9.2s
  srshl v7.2s, v8.2s, v9.2s
  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)0307191e3f51inst 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)60696b6d6edispatch 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
80204200581500004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100009511021611200360800001002004020040200402004020040
802042003915000184025801001008000010080000626640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100030511011611200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000026425801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100030511011611200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100010511011611200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000511011613200360800001002004020040200402004020040
80204200391500004125801251258000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000511012711200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa8accfd0d2d5d6dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150004025800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010205020001616001111200360080000102014420040200402004020040
8002420039150004025801111080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010005020001316001211200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010005020001216001314200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010005020001316001013200360080000102008920040200402004020040
8002420039150004025800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010005020001216001212200360080000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999602610019800102080000201600002003920039118002110910108000010005020001316001311200360080000102004020040200402004020040
80024200391501244025800101080000108000050640000120020200392003999960310019800102080000201600002003920039118002110910108000010005020001216001112200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010005020001216001112200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010005020001316001013200360080000102004020040200402004020040
80024200391500020062580010108000010800005064000002002020039200399996031001980010208000020160000200392003911800211091010800001000502000131600129200360080000102004020040200402004020040