Apple M1 Microarchitecture Research by Dougall Johnson

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

UQRSHL (vector, 2D)

Test 1: uops

Code:

  uqrshl v0.2d, v0.2d, v1.2d
  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
10043037230842548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230822548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230822548251000100010003983133018303730842418328951000100020003037303711100110000073116112630100030383038303830383038
10043037220822548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372301032548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220842548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230842548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230822548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqrshl v0.2d, v0.2d, v1.2d
  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)0308181e3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129706100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130300183300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250017461295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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
1002430037225000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037226000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006401162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037224000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373007811100211091010100001000000006402162229630010000103003830038300383003830038
1002430037224000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqrshl v0.2d, v1.2d, v0.2d
  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)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)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225648107295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296341100001003003830038300383003830038
102043003722537261295482510100100100001001000050042773130300183003730037282653287451073220010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722547761295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722555261295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722559161295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722551961295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722445361295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011610296340100001003003830038300383003830038
102043003722538761295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071001611296340100001003003830038300383003830038
10204300372254261295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722548061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722503061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640416352963010000103003830038300383003830038
100243003722500251295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250661295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722400156295482510010101000010100005042773130300183003730037282873287671001020100002020000300843003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372540061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373008311100211091010100001000640316332963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqrshl v0.2d, v8.2d, v9.2d
  uqrshl v1.2d, v8.2d, v9.2d
  uqrshl v2.2d, v8.2d, v9.2d
  uqrshl v3.2d, v8.2d, v9.2d
  uqrshl v4.2d, v8.2d, v9.2d
  uqrshl v5.2d, v8.2d, v9.2d
  uqrshl v6.2d, v8.2d, v9.2d
  uqrshl v7.2d, v8.2d, v9.2d
  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)030818191e1f3f51inst 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
80204200581500000041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021611200360800001002004020040200402004020040
802042003914900060516258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500000062258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500000083258010010080000100800005006400000200202003920039997339997801002008031020016000020039200933180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391501000041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420039150000183041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500009041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500009041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500000041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915000012041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e3f51inst 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)9fcfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915002795025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010502053416662003680000102004020040200402004020040
80024200391500484025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010502053416342003680000102004020040200402004020040
80024200391500214025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010502053416432003680000102011420100200402004020040
8002420039150004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010502053416352003680000102004020040200402004020040
80024200391500184025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010502053316342003680000102004020040200402004020040
8002420039150004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010502053616682003680000102004020040200402004020040
8002420039150004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010502053316432003680000102004020040200402004020040
80024200391500274025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010502053416472003680000102004020040200402004020040
8002420039150004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010502053416442003680000102004020040200402004020040
8002420039150004025800101080000108000050640000052002020039200399996310019800102080000201600002003920039118002110910108000010502053416442003680000102004020040200402004020040