Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMS (vector, 2D)

Test 1: uops

Code:

  fcvtms v0.2d, v0.2d
  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
100430372408225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414728951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtms v0.2d, v0.2d
  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)030b1e3f4e51inst 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
10204300372320061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771600300660300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723300251295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372320061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372330071295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372320061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100307101161129633100001003003830038300383003830038
10204300372331061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723300251295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723200612954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830121
100243003723300612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000064002162229629010000103003830038300383003830038
100243003723300612954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001020064002162229629010000103003830038300383003830038
100243003723300612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001010064022162229690010000103003830038300383003830038
100243003723300892954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001010064002162229629010000103003830038300383003830038
1002430037233007262954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001010064002162229629010000103003830038300383003830038
100243003723300612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001010064002162229629010000103003830038300383003830038
100243003723300612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001020064002162229629010000103003830038300383003830038
100243003723200612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001030064002162229629010000103003830038300383003830038
100243003724100612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000364002162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtms v0.2d, v8.2d
  fcvtms v1.2d, v8.2d
  fcvtms v2.2d, v8.2d
  fcvtms v3.2d, v8.2d
  fcvtms v4.2d, v8.2d
  fcvtms v5.2d, v8.2d
  fcvtms v6.2d, v8.2d
  fcvtms v7.2d, v8.2d
  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)031e1f3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd0d2d5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581550030258010810080008100800205006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511800116000200360800001002004020040200402004020040
80204200391550030258010810080008100800205006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010010111511800016000200360800001002004020040200402004020040
802042003915512030258010810080008100800205006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511800016000200360800001002004020040200402004020040
802042009215500505258010810080008100800205006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511800016000200360800001002004020040200402004020040
802042003915500410258010810080008100801285006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010003111511800016000200360800001002004020040200402004020040
80204200391560030258010810080008100800205006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511800016000200360800001002004020040200402004020040
80204200391556072258010810080008100800205006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511800016000200360800001002004020040200402004020040
80204200391550030258010810080008100800205006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511800016000200360800001002004020040200402004020040
80204200391560030258010810080008100800205006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511800016000200360800001002004020040200402004020040
80204200391550030258010810080008100800205006401321020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511800016000200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3a3f51inst 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)cfd5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915500040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020716662003612780000102004020040200402004020040
8002420039155000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050203166620036109080000102004020040200402004020040
800242003915500040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020516752003659080000102004020040200402004020040
800242003915600040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020516532003673080000102004020040200402004020040
800242003915500040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020516652003658080000102004020040200402006220040
800242003915600040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020316352003657080000102004020040200402004020040
800242003915600014925800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502051653200360080000102004020040200402004020040
800242003915590040025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010030502031655200360080000102004020040200402004020040
80024200391550007525800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502031635200360080000102004020040200402004020040
80024200391560008625800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502031635200360080000102004020040200402004020040