Apple M1 Microarchitecture Research by Dougall Johnson

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

RSHRN (8H)

Test 1: uops

Code:

  rshrn v0.8b, v0.8h, #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
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383123303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723019025472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  rshrn v0.8b, v0.8h, #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)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)696b6d6edispatch 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)9fa6a8cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240612954725101001001000010010000500427716030018030037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038301803003830038
10204300372250612954725101001001000810010450500427716030018030037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018030037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372256612954725101001001000010010000500427716030018030037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018030037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716030018030037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830134300383003830038
10204300372250612954725101001001000010010000500427851230018030037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018030037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018030037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018030037300372826403287451010020010000200100003003730037111020110099100100100001002007101161129633100001003003830038300383003830038

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)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)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001001064021622296290010000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064021622296290010000103003830038300383003830038
10024300372250232295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064021622296290110000103008530038300383003830038
1002430037225061295472510010101000010101505042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064021622296290010000103003830038300383003830038
1002430037225061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000064021622296290010000103003830038300383003830038
1002430037224061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064021622296290010000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064021622296290010000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064021622296290010000103003830085300383003830038
1002430037225061295472510010101000010100005042771601300183003730037282973287671001020100002010000300373008411100211091010100001000064021622296290010000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064021622296290010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  rshrn v0.8b, v8.8h, #3
  rshrn v1.8b, v8.8h, #3
  rshrn v2.8b, v8.8h, #3
  rshrn v3.8b, v8.8h, #3
  rshrn v4.8b, v8.8h, #3
  rshrn v5.8b, v8.8h, #3
  rshrn v6.8b, v8.8h, #3
  rshrn v7.8b, v8.8h, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03070a1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200691501103025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010005411151181161120036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001001011151181161120036800001002004020040200402004020040
8020420039150110352580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150110722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002024720040200402004020040
8020420039150110302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039218020110099100100800001002115311151181161120036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391501102672580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391501107225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010030011151181161220036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040

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)5f696b6d6edispatch 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)9fa8cdcfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000502009316112003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000502009216112003680000102004020040200402004020040
8002420039155061258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000502008116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001001502009116112003680000102004020040200402004020040
8002420039150061258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000502009116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200200200392003999963100198001020801052080000200392003911800211091010800001000502009116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000502009216112003680000102004020040200402004020040
8002420039150061258001010800121080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000502009116112003680000102004020040200402004020040
8002420039150040258001010800001080000506407880200200200392003999963100198001020800002080000200392003911800211091010800001000502009116122003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200200200392003999963100198001020801402080000200392003911800211091010800001000502009116212003680000102004020040200402004020040