Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHRN (S)

Test 1: uops

Code:

  uqshrn h0, s0, #3
  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)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
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001373116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqshrn h0, s0, #3
  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)030b3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000171011611296330100001003003830038300383003830038
10204300372251612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071021611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722402562954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b1e3f4e51inst 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)9fa0a1a6a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372240006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000016403163329629010000103003830038300383003830038
10024300372240006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000833806403163329629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000606403163329629010000103003830038300383003830038
10024300372240006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372240006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001020000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqshrn h0, s8, #3
  uqshrn h1, s8, #3
  uqshrn h2, s8, #3
  uqshrn h3, s8, #3
  uqshrn h4, s8, #3
  uqshrn h5, s8, #3
  uqshrn h6, s8, #3
  uqshrn h7, s8, #3
  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)03090b1e1f3f51inst 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)9fa0a1a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000010011151182162120036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000040011151182162120036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151182162220036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161220036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151182162120036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151182162220036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161220036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000010011151182162220036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151182162220036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151182162120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa0a1a6a8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020101621162003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000050209162192003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100001000502021161892003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502021169212003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502021169212003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000050209162192003680000102004020040200402004020040
800242003915000515258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000130050208169212003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005130050209169212003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000044300502021169212003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100001000502021169212003680000102004020040200402004020040