Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAS (vector, 4S)

Test 1: uops

Code:

  fcvtas v0.4s, v0.4s
  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)03070a191e3f4e51inst 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
100430372500036125472510001000100039816013018303730372414328951000100010003037303711100110000073216212629100030383038303830383038
1004303726100310325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240002122925472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303725000186125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372500006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400006125472510001000100039816013018303730372414328951000100010003037303711100110000373124112626100030383038303830383038
1004303724000156125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372400006225472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724100546125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtas v0.4s, v0.4s
  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)033f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722561295472510100100100001001000050042771601300183003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722561295472510100100100001001000050042771600300183003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722461295472510100100100001001000050042771600300183003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722561295472510100100100001001000050042771600300183003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722561295472510100100100001001000050042771600300183003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722561295472510100100100001001000050042771600300183003730037282640328745101002001000020010000300373003711102011009910010010000100107101161129633100001003003830084300383003830038
102043003722561295472510100100100001001000050042771600300183003730037282640328745101002001000020210000300373003711102011009910010010000100007101161029633100001003003830038300383003830038
102043003722461295472510100100100001001000050042771600300183003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722561295472510100100100001001000050042771600300183003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722561295472510100100100001001000050042771600300183003730037282640328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

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)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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372320612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000640316222962910000103003830038300383003830038
100243003723207262954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000100640216222962910000103003830038300383003830038
10024300372330612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003723307262954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372320612954725100101010000101000050427716003001803008530037282913287671001020100002010000300373003711100211091010100001000030640216222962910000103003830038300383003830038
10024300372330612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003723307262954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372330822954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372320612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372330612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000130640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtas v0.4s, v8.4s
  fcvtas v1.4s, v8.4s
  fcvtas v2.4s, v8.4s
  fcvtas v3.4s, v8.4s
  fcvtas v4.4s, v8.4s
  fcvtas v5.4s, v8.4s
  fcvtas v6.4s, v8.4s
  fcvtas v7.4s, v8.4s
  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)0318191e1f3f51inst 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)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049156000053258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100031115118116020036800001002004020040200402004020040
8020420039156000051258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
8020420039155000051258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915500001734258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
8020420039156000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550000102258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550000169258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550000505258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
8020420039155000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550000212258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a191e3f51inst 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)6061696d6edispatch 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)9fa8accfd0d2icache miss (d3)d5d6daddinst fetch restart (de)e0eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511560004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000101050205002160112003600080000102004020040200402004020040
80024200391560006125800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100050205301160112003600080000102004020040202452004020040
8002420039155000182625800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100350205301160112003600080000102004020040200402010020154
800242003915500070525801071080000108000061640000152002020039200399996310019800102080000208000020039200391180021109101080000101050205401160112003600080000102004020040200402004020040
80024200391550006825800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000102050200401160112003600080000102004020040200402004020040
80024200391550004025800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000103050205401160112003600080000102004020040200402004020040
8002420039161101819425800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050200001160112003600080000102004020040200402004020040
80024200391560004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000103050200001160112003600080000102004020040200402004020040
80024200391550004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050200001160112003600080000102004020040200402004020040
80024200391560004025800101080000108000050640000102006120039200391000531001980010208000020800002003920039118002110910108000010435020000116011200360023080000102004020040200402004020040