Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHRN (2D)

Test 1: uops

Code:

  uqshrn v0.2s, v0.2d, #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)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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372206125472510001000100039816030543037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724148289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqshrn v0.2s, v0.2d, #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)60696b6d6edispatch 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240612954725101001001000010010000500427716013001803003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001803003730037282640728762101002001000020010000300373003711102011009910010010000100107101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001803003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001803003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001803003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001803003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001803003730037282640328745101002001000020010000300373003711102011009910010010000100028817101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001803003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722518612954725101001001000010010000500427716013001803003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001803003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b0e18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372250000000008929547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160130018030037300372828632881410010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000500064021622296290010000103003830038300383003830038
10024300372240000000006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000302606064021622296290010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300842250000006006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqshrn v0.2s, v8.2d, #3
  uqshrn v1.2s, v8.2d, #3
  uqshrn v2.2s, v8.2d, #3
  uqshrn v3.2s, v8.2d, #3
  uqshrn v4.2s, v8.2d, #3
  uqshrn v5.2s, v8.2d, #3
  uqshrn v6.2s, v8.2d, #3
  uqshrn v7.2s, v8.2d, #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)033f51inst 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)9fa6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181160020036800001002004020040200402004020040
8020420039150600258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002009020040200402004020040
8020420039150915258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100003011151180160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100013011151180160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040

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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150113220125800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100005020416442003680000102004020040200402004020040
80024200391500128025800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100005020516332003680000102004020040200402004020040
8002420039150007425800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000101005020516332003680000102004020040200402004020040
80024200391500010325800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100015020516532003680000102004020040200402004020040
80024202441500074258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001002405020416532003680000102004020040200402004020040
8002420039150007425800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100005020416552003680000102004020040200402004020040
8002420039150007425800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100005020416342003680000102004020040200402004020040
8002420039150008125800101080000108000050640000020020200392003999960810019800102080000208000020039200391180021109101080000100005020316342003680000102004020040201002004020040
8002420039150007425800101080000108000050640000020029200392003999960310019800102080000208000020039200391180021109101080000100005020416452003680000102004020040200402004020040
8002420039150008125800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100305020416452003680000102004020040200402004020040