Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTNS (scalar, H to X)

Test 1: uops

Code:

  fcvtns x0, h0
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 2.000

Issues: 3.000

Integer unit issues: 1.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 2.000

retire (01)cycle (02)03081e3f51inst issue (52)~issue int (53)~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 integer (97)a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
20045414004325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
20045414005625300010002000200018000152254154124832742000200020005415411110011000007311611538100010001000542542542542542
20045414004325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
20045414008725300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
20045414008725300010002000200018000052254154124832742000200020005415411110011000007511611538100010001000542542542542542
20045415008525300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
20045414004325300010002000200018000052254154124832742000200020005415411110011000007511611538100010001000542542542542542
20045414004325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
20045414004325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
20045414004325300010002000200018000052254154124832742000200020005415411110011000107311611538100010001000542542542542542

Test 2: Latency 1->2 roundtrip

Code:

  fcvtns x0, h0
  fmov d0, x0
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 13.0038

retire (01)cycle (02)0308090b18191e1f3a3f4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
302051300609740000000013002311941725401001010020000100001002000010000500621497914801034113003301300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001000010000000000131012162212952510000100001000010100130039130039130039130039130039
3020413003897400000000130023119417254010010100200001000010020000100005006214979148010341130013013003813003812547631262463010020010000200002001000020000130038130038212020110099100101001000010000100002200000131012162212952510000100001000010100130039130039130039130039130042
302041300389740000000013002311941725401001010020000100001002000010000500621497914801034013001301300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001000010000000000131012162212952510000100001000010100130039130039130039130039130039
302041300389740000000013002311941725401001010020000100001002000010000500621741314801373113001301300381300381254763126246301002001000020000200100002000013007013003811202011009910010100100001000010000000000131012162212952510000100001000010100130039130039130039130039130041
302041300389740000000013002311941725401001010020000100001002000010000500621512314801034013001301300381300381254763126246301002001000020000200100642000013003813003811202011009910010100100001000010000103000131012162212952510000100001000010100130039130039130039130039130039
302041300389740000000013002311941725401001010020000100011002000010000500621497914801034113001301300381300421254763126246301002001000020000200100002000013003813003811202011009910010100100001000010000000000131012162212952510000100001000010100130039130039130041130039130039
302041300389740010000013002311941725401001010020000100001002000010000500621497914801034113001601300381300451254763126246301002001000020000200100002000013003813003811202011009910010100100001000010000000000131012162212952510000100001000010100130039130039130039130039130039
302041300389740000000013002311941725401001010020000100001002000010000500621497914801034013001301300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001000010000000000131012162212952510000100001000010100130039130039130040130039130039
302041300389750102218688013002311941725401001010020000100001002000010000500621497914801376013001301300381300381254763126247301002001000020000200100002000013003813003811202011009910010100100001000010000003000131013163212952510000100001000010100130039130039130039130039130039
302041300389740000060013002311941725401001010020000100001002000010000500621497914801034013001301300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001000010000000000131013162212952510000100001000010100130039130039130039130039130039

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0038

retire (01)cycle (02)03080b1e1f3f4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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)9fa6a8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ebld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
30024130038974000013002311941725400101001020000100001020000100005062149791480002501300133130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010100000000127031644129525100000100001000010010130041130052130039130039130039
30024130038988000013002311941725400101001020003100001020000100005062149791480002501300130130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010100000000127051633129525100000100001000010010130052130039130039130039130039
30024130038974000013002311941725400101001020000100001020000100005062149791480002501300160130040130038125500312626830334221024620000201000020000130038130038112002110910100101000010100000000127051654129525100000100001000010010130039130039130039130039130039
30024130038974000013002311942225400101001020000100001020000100005062149791480002501300130130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010100000000127061645129525100000100001000010010130063130039130039130039130039
30024130038974000013002311941725400101001020000100001020000100005062149791480002501300130130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010100000000127041655129528100000100001000010010130044130078130042130039130039
30024130041974000013002311941725400101001020000100001020000100005062149791480002501300130130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010100000000127041655129525100000100001000010010130043130039130039130039130039
30024130038974000013004911941725400101001020000100101020000100005062149791480036701300130130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010100000300127051656129525100000100001000010010130067130039130039130039130039
30024130038973000013002311941725400101001020000100001020000100005062149791480002501300130130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010100000000127061646129525100000100001000010010130045130039130039130039130039
30024130038974000013002311941725400101001020000100001020000100005062149791480002501300130130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010100000000127041645129525100000100001000010010130040130039130039130039130039
30024130038974000013002311941725400101001020000100001020000100005062149791480002501300130130038130038125498312626830010201000020000201000020126130078130038212002110910100101000010100000000127041645129525100000100001000010010130040130039130039130039130039

Test 3: throughput

Count: 8

Code:

  fcvtns x0, h8
  fcvtns x1, h8
  fcvtns x2, h8
  fcvtns x3, h8
  fcvtns x4, h8
  fcvtns x5, h8
  fcvtns x6, h8
  fcvtns x7, h8
  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5005

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044012531100002400322524010480100160004100160020500144013214002240041400411997761999216012020016003220016003240041400411180201100991008010010000000000111511701600402928000080000801004004240042400424004240042
160204400413110000000322524010480100160004100160020500144013214002240041400411997761999216012020016003220016003240041400411180201100991008010010000000000111511701600400388000080000801004004240042400424004240042
160204400413110000000322524010480100160004100160020500144013204002240041400411997761999216012020016003220016003240041400411180201100991008010010000000000111511701600400388000080000801004004240042400424004240042
160204400413100000000322524010480100160004100160020500144013214002240041400411997761999216012020016003220016003240041400411180201100991008010010000001000111511701600400388000080000801004004240042400424004240042
160204400413110000000532524010480100160004100160020500144013214002240041400411997761999216012020016003220016003240041400411180201100991008010010000000000111511701600400388000080000801004004240042400424004240042
1602044004131000000002462524010480100160004100160020500144013214002240041400411997761999216012020016003220216003240041400411180201100991008010010000000000111511701600403008000080000801004004240042400424004240042
1602044004131000001200322524010480100160004100160020500144013214002240041400411997761999216012020016003220016003240041400411180201100991008010010000001000111511701600400388000080000801004004240042400424004240042
160204400413110000000322524010480100160004100160020500144013214002240041400411997761999216012020016003220016003240041400411180201100991008010010000000000111511701610400388147080000801004116741243412344115041246
160204412433190016152112132015951376244734814261633161061632285051469331141121412874130320386619992160120200160032200160032400414004111802011009910080100100222002706801115413016021410848106680000801004130441340413134129641313
16020441316321111615224479213225240104801001600041001600205001440132040855409934084420237110205681628022001626222001618784092241066131802011009910080100100020000878521115378015100410098133880000801004067541240413204123741330

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5005

retire (01)cycle (02)030b1e3a3f51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004230000084325240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000005020516032400388000080000800104004240042400424004240042
16002440041300000137125240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000005020316042400388000080000800104004240042400424004240042
16002440041300000184425240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000005020316043400388000080000800104004240042400424004240042
16002440041300000112225240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000005020316052400388000080000800104004240042400424004240042
16002440041300000110125240010800101600001016000050144000000400694004140041199963200211600102016000020160000400414004111800211091080010100000005020316032400388000080000800104004240042400424004240118
1600244004129900076725240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000005020316033400388000080000800104004240042400424004240042
16002440041300000153625240010800101600001016000050144149800400224004140041199963200211600102016000020160000400414004111800211091080010100000005020216034400388000080000800104004240042400424004240042
16002440041312000108925240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000005020316033400388000080000800104004240042400424004240042
16002440041299000129225240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000105020316032400388000080000800104004240042400424004240042
16002440041300000142325240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000005020316033400388000080000800104004240042400424004240042