Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDLV (vector, 8H)

Test 1: uops

Code:

  uaddlv s0, v0.8h
  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)030b1e3f4e51inst 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
1004303723006125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230010125472510001000100039816003018303730372414328951000100020003037303711100110000073116222629100030383038303830383038
1004303723006125472510001000100039816013018303730372413328951000100020003037303711100110000073116222629100030383038303830383038
1004303723008225472510001000100039816003018303730372414328951000100020003037303711100110002073116112629100030383038303830383038
10043037230246125472510001000100039816003018303730372414328951000100020003037303711100110006073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100020003037303711100110002073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100020003037303711100110006073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uaddlv s0, 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)0308191e3f4e51inst 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)9fa0a1a8a9acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250027661295472510100100100001001000050042771601300180300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771601300180300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296331100001003003830038300383003830038
1020430037225001861295472510100100100001001000050042771601300180300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722500180256295472510100100100001001000050042771601300180300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225001561295472510100100100001001000050042798641300180300373003728264328745101002001000020020000300373003721102011009910010010000100420729100071011611296330100001003008530133300383003830038
1020430037224000441295472510100100100001001000050042785121300180300373003728264328745101002041000020020000300373003711102011009910010010000100000040700071011611296330100001003003830038300383003830038
10204300372250027124295472510100100100001001000050042771601300180300373003728264328745104172001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225001861295472510100100100001041000050042771601300180300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037224002161295472510100100100001001000050042771601300180300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372250027661295472510100100100001001000050042771601300180300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038

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)9fa0a1a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000009906404163329629010000103003830038300383003830038
10024300372250100000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000007506403163329629010000103003830038300383003830038
1002430037225000000082295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000306403163329629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372240000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000012106403163329629010000103003830038300383003830038
1002430037225001100061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000306403163329629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001002000306403163329629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000306403163329629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000606403163329629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000306403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uaddlv s0, v8.8h
  uaddlv s1, v8.8h
  uaddlv s2, v8.8h
  uaddlv s3, v8.8h
  uaddlv s4, v8.8h
  uaddlv s5, v8.8h
  uaddlv s6, v8.8h
  uaddlv s7, v8.8h
  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)03070a181e1f3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591501100030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100016511151181161120036800001002004020040200402004020040
8020420039150110120132302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000311151181161120036800001002004020040200402004020040
802042003915011000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000611151181161120036800001002004020040200402004020040
8020420039150110003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001511151181161120036800001002004020040200402004020040
802042003915011000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150110003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001211151181161120036800001002004020040200402004020040
802042003915011000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000311151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa8acbranch mispredict (cb)cfd0d5d6ddinst fetch restart (de)dfe0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391510146258001010800001080000506400001200202003920039999603100198001020800002016000020039200391180021109101080000102305022614162622003680000102004020040200402004020040
8002420039150014625800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010090502266162622003680000102004020040200402004020040
8002420039150014625800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010000502262162222003680000102004020040200402004020040
80024200391500046258001010800001080000506400001200202003920039999603100198001020800002016000020039200391180021109101080000100120502202166222003680000102004020040200402004020040
80024200391500146258001010800001080000506400001200202003920039999603100198001020800002016000020039200391180021109101080000100150502266162222003680000102004020040200402004020040
8002420039150014625800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010090502262162222003680000102004020040200402004020040
8002420039150014625800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010000502266162222003680000102004020040200402004020040
8002420039150014025800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010000502262162222003680000102004020040200402004020040
8002420039150014625800101080000108000050640000020020200392003999960310019800102080000201600002003920039118002110910108000010000502266166222003680000102004020040200402004020040
8002420039150014625800101080000108000050640000120020200392003999960310019800102080000201600002003920039118002110910108000010000502262166222003680000102004020040200402004020040