Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTP (vector, 8H)

Test 1: uops

Code:

  frintp v0.8h, 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)03071e3f4e51inst 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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372400822547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372400612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372400612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000020073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372400612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372400612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372400612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372400612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
1004303724012612547251000100010003981600301830373037241432895100010001000303730371110011000001073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintp v0.8h, 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)03080a1e1f3f4e5051inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225020061295472251010010010000100100005004277160130018030037300372826432874510100200100002141000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
102043003722502570612954702510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100011273521622296330100001003003830038300383003830038
1020430037225020061295470251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
102043003722502120061295470251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
1020430037225020061295470251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
10204300372250212061295470251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
1020430037225020061295470251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
102043003722502300536295470251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
1020430037224020061295470251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
102043003722502240103295470251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308191e3a3f4e51inst 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000384129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722410006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037225000019329547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722400006129547251001010100001010000504277160030018300373003728286328767101592010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037235000015129547251001810100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006404162229629010000103003830038300383003830038
100243003722400006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402161229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722400006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintp v0.8h, v8.8h
  frintp v1.8h, v8.8h
  frintp v2.8h, v8.8h
  frintp v3.8h, v8.8h
  frintp v4.8h, v8.8h
  frintp v5.8h, v8.8h
  frintp v6.8h, v8.8h
  frintp v7.8h, 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)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)9fa7a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058155001230258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100100011151180160020036800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100023011151180160020036800001002004020040200402004020040
802042003915500030258010810080008100800205006401320200572003920039997769990801202008003220080032200392003911802011009910010080000100000011151182162020036800001002004020040200402004020040
802042003915500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048155072822580010108000010800005064000012002002003920039999631001980010208000020800002003920039118002110910108000010105020416332003680000102004020040200402004020040
800242003915600402580010108000010800005064000002002002003920039999631001980010208032120800002003920039118002110910108000010035020216552003680000102004020040200402004020040
800242003915510402580010108000010800005064000002002002003920039999631001980010208000020800002003920039118002110910108000010035020316552003680000102004020040200402004020040
800242003915503402580010108000010800005064000002002002003920039999631001980010208000020800002003920039118002110910108000010005020516362003680000102004020040200402004020040
8002420039155027402580010108000010800005064000002002002003920039999631001980010208000020800002003920039118002110910108000010005020316532003680000102004020040200402004020040
800242003915500402580010108000010800005064000002002002003920039999631001980010208000020800002003920039118002110910108000010105020316552003680000102004020040200402004020040
800242003915600402580010108000010800005064000002002002003920039999631001980010208000020800002003920039118002110910108000010005020516232003680000102004020040200402004020040
800242003915500402580010108000010800005064000002002002003920039999631001980010208000020800002003920039118002110910108000010095020316332003680000102004020040200402004020040
800242003915500402580010108000010800005064000002002002003920039999631001980010208000020800002003920039118002110910108000010005020616532003680000102004020040200402004020040
8002420039155039402580010108000010800005064000002002002003920039999631001980010208000020800002003920039118002110910108000010005020216232003680000102004020040200402004020040