Apple M1 Microarchitecture Research by Dougall Johnson

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

UQXTN (D)

Test 1: uops

Code:

  uqxtn s0, d0
  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)033f4e51inst 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
1004303722612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723612547251000100010003981603018303730372414328951000100010003037303711100110000073124112629100030383038303830383038
100430372315625472510001000100039816030183037303724143289510001000100030373037111001100034073116112629100030383038303830383038
1004303723612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037226125472510001000100039816030183037303724143289510001000100030373037111001100015073116112629100030383038303830383038
1004303723612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqxtn s0, d0
  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)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)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722505362954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722502512954725101001001000010010000500427716030018300373003728264328745101002001000020010000300853008421102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037225018592954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038

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
1002430037233000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730084282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqxtn s0, d8
  uqxtn s1, d8
  uqxtn s2, d8
  uqxtn s3, d8
  uqxtn s4, d8
  uqxtn s5, d8
  uqxtn s6, d8
  uqxtn s7, d8
  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)9fa1c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915030258010810080008100800205006401320200202003920039997769990802322008003220080032200392003911802011009910010080000100011151182162220036800001002010220100200652009920148
802042010615030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182161220036800001002004020040200402004020040
802042003915051258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182162220036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181161220036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182162120036800001002004020040200402004020040
802042003915030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182162220036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182162120036800001002004020040200402004020040
802042003915030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181161220036800001002004020040200402004020040
802042003915030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182161220036800001002004020040200402004020040
802042003915093258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181162220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3a3f51inst 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)5f60696d6edispatch 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)9fa1acc2cfd5d6dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100005020101600562003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000502091600662003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000502071600562003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631004580329208000020800002003920039118002110910108000010000502071600542003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000502091600552003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000502081600662003680000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000502081600762003680000102004020040200402004020040
8002420089150000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010030502091600562003680000102004020040200402004020040
8002420039150000402580106108000010800005064000011200202003920039999631004780010208000020800002003920039118002110910108000010000502071600762003680000102004020040200402004020040
8002420039150000402580010108000010800005064000010200202003920039999631001980010208000020800002003920039118002110910108000010000502071600552003680000102004020040200402004020040