Apple M1 Microarchitecture Research by Dougall Johnson

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

UCVTF (scalar, integer, H from W)

Test 1: uops

Code:

  ucvtf h0, w0
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 2.000

Issues: 2.000

Integer unit issues: 0.000

Load/store unit issues: 1.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4f51inst issue (52)~issue fp/simd (54)~issue ld/st (55)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing ld/st (5a)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op ld/st (7d)~map op fp/simd (7e)~map lookup ld/st (80)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a6accfd5d6ddinst fetch restart (de)e0eald/st retires (ed)? fp/simd (ee)f5f6f7f8fd
2004376303610252000100010001000100014075228200357376376723109200010001000100010003763761110011000100007311611373010001000377377377377377
2004376303610252000100010001000100014075228200357376376723109200010001000100010003763761110011000100007311611373010001000377377377377377
2004376303610252000100010001000100014075228200357376376723109200010001000100010003763761110011000100007311622373010001000377377377377377
2004376303610252000100010001000100014075228200357376376723109200010001000100010003763761110011000100007311611373010001000377377377377377
2004376203610252000100010001000100014075228200357376376723111200010001000100010003763761110011000100007321611373010001000377377377377377
2004376303610252000100010001000100014075228200357376376723109200010001000100010003763761110011000100007311622373010001000377377377377377
2004376303610252000100010001000100014075228200357382376723109200010001000100010003763761110011000100007311611373010001000377377377377377
2004376303610252000100010001000100014075228200357376376723109200010001000100010003763761110011000100007311611373010001000377377377377377
2004376303610252000100010001000100014075228200357376376723109200010001000100010003763761110011000100007321622373010001000377377377377377
2004376303610252000100010001000100014075228200357376376723109200010001000100010003763761110011000100007321611373010001000377377377377377

Test 2: Latency 1->2 roundtrip

Code:

  ucvtf h0, w0
  fmov x0, d0
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 13.0032

retire (01)cycle (02)03080b191e1f3f4f51inst 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)9fa6a8acc2branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)eald/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
302041300329730000013001711940825401001010020000100001002000010000500621449714802709113005501300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001001000000001310121622129519100000100001000010100130033130033130033130033130033
302041300329740000013001711940825401001010020000100001002000010000500621500114804173113001301300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001001000010001310121622129520100000100001000010100130033130033130033130033130033
302041300329740000013001711940825401001010020000100001002000010000500621449714802709113001301300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001001000000001310121622129519100000100001000010100130033130033130033130033130033
3020413003297401000130017119408254010010100200001000010020000100005006214497148027090130013013003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000036001310121622129519100000100001000010100130033130033130033130033130033
302041300329740000013001711944925401001010020000100011022011810000500621468914802709013001301300321300321254663126240301002001000020000202110452060913062113087341202011009910010100100001001000000001310131623129519100000100001000010100130033130033130033130033130033
302041300379740000013001711940825401001010020000100001002000010000500621449714802709013001301300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001001000000001310121622129519100000100001000010100130033130033130033130033130033
302041300329740000013001711940825401001010020000100001002000010000500621449714802709013001301300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001001000000001310121622129519100000100001000010100130033130033130033130033130033
302041300329730000013001811940832401001011920000100001002012110000500621459314802709013001301300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001001000000001310121623129519100000100001000010100130033130033130033130033130033
302041300329740000013001711940825401001010020000100001002000010000500621449714802709013001301300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001001000000001310121622129519100000100001000010100130033130033130033130033130033
302041300329731000013001711940825401001010020000100001002000010000500621449714802709013001301300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001001000000001310121632129519100000100001000010100130033130039130033130033130033

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0032

retire (01)cycle (02)0318191e1f3f4f51inst 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)60696d6edispatch 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
30024130032974000013001711941225400101001020009100001020000100005062144971480064101300131300321300331254893126265301762010061200002010000200001300321300321120021109101001010000100010000000000012702162112951910000100001000010010130034130033130065130033130033
30024130032974109013006311940825400101001320000100001020000100005062144971480052801300151300321300321254893126263300102010000200002010000201231300321300321120021109101001010000100010000000000012701161212958310001100001000010010130033130033130197130033130033
300241300329730098813001911940846400161001020000100041020113100006062144971480052801300141301191300321254893126262300102010000200002010000201231300321300782120021109101001010000100110000010001012705161112951910002100001000010010130033130034130034130034130126
30024130032974000013001711940825400101001020000100001020000100005062144971480052801300131300321300321254893126262300102010000200002010000200001300321300321120021109101001010000100010000000000012891161112951910000100001000010010130033130033130033130033130033
30024130032974000013001711940825400101001020000100001020000100005062144971480052801300131300321300321254893126262300102010000200002010000200001300321300321120021109101001010000100010000000000012701161112951910000100001000010010130033130033130033130033130033
30024130032973000013001711940825400101001020000100001020000100005062144971480052801300611300321300321254893126262300102010000200002010000200001300651301091120021109101001010000100010000000000012701161212951910000100001000010010130033130033130033130033130033
30024130033974000013001711940825400101001020000100001020000100005062144971480052801300131300321300321254893126262300102010000200002010000200001300321300321120021109101001010000100010000000000012702161212951910000100001000010010130033130033130033130033130033
30024130032974000013001711940825400101001020000100001020000100005062153851480052801300131300321300321254893126262300102010000200002010000200001300321300321120021109101001010000100010000000000012701161112951910000100001000010010130033130033130033130033130033
30024130032973000013001711940825400101001020000100001020000100005062144971480052801300131300321300321254893126283300102010000200002010000200001300321300321120022109101001010000100010000000000012701161112951910000100001000010010130033130033130033130033130033
300241300329730000130017119408254002310010200061001410200001014750621653414816402113099313118913077012582639126426308392010917208512010920215181307851300821120021109101001010000100210009012427500012701161112951910000100001000010010130033130076130033130033130033

Test 3: throughput

Count: 8

Code:

  ucvtf h0, w8
  ucvtf h1, w8
  ucvtf h2, w8
  ucvtf h3, w8
  ucvtf h4, w8
  ucvtf h5, w8
  ucvtf h6, w8
  ucvtf h7, w8
  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3339

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)6061696b6d6edispatch stall (70)72scheduler 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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020426711207000000002670402516010010080000800001008002080015500116952418858081026690026709267206632066661160135200800208002420080020800202670926714118020110099100100800001000080000030111511703161226706080000800001002671026710267102671026710
16020426709200000000002669402516010010080000800001008002080015500116895118841630026690026709267096632066658160135200800208002020080020800202670926709118020110099100100800001000080000000111511701162226751080000800001002671026710267102671026710
16020426709200000000002670502516010010080000800001008002080015500116895118842761026690026709267096632066658160135200800208002020080020800202670926709118020110099100100800001000080000000111511703162126706080000800001002671026715267102671626717
160204267092000000012002670902516010010080000800001008002080015500116895118841630026694026717267236632066658160135200800208002020080020800202670926709118020110099100100800001000080000000111511702161226706080000800001002671026710267102671026710
160204267092000000039002678802516010010080000800001008002080015500116895118841630026690026709267096632066658160135200800208002020080020800202671326709218020110099100100800001000080000060111511702162226706080000800001002671026710267102671026710
16020426709200000000002675502516010010080000800001008002080015500116895118841630026690026709267096632066658160135200800208002020080020800202671026709118020110099100100800001000080000000111511702162226874080000800001002671026710267102671026710
16020426709200000000002672522516010010080000800001008002080015500116895118841630026690026709267096632066658160135200800208002020080020800202670926709118020110099100100800001000080000000111514202162226706080000800001002671026710267102671026710
16020426709200000000002671602516010010080000800001008002080015500116895118841630026690026709267096632066658160135200800208002020080020800202670926709118020110099100100800001000080000000111511702162126706080000800001002671026710267102671026710
16020426709200000000002676402516010010080000800001008002080015500116895118841630026690026709267096632066658160135200800208002020080020800202670926709118020110099100100800001000080000000111511702161226706080000800001002671026713267102672926710
16020426709200000000002670602516010010080000800001008002080015500116895118841630026690026709267096632066658160135200800208002020080020800202670926709118020110099100100800001000080000000111511702162226706080000800001002671026710267102671026710

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3339

retire (01)cycle (02)0318191e1f3f4f51inst 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)6061696d6edispatch 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)9fa5a6a8acbranch mispredict (cb)cdcfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242670920000002669422516001010800008000010800008000050116888018840321526690267092670966533668916001020800008000020800008000026709267091180021109101080000100800000600502052051664267068000080000102671026761267982671626716
1600242670919900002669402516001010800008000010800008000050116888018840321526690267092670966533668916001020800008000020800008000026709267091180021109101080000100800004000502052041643267068000080000102685126829267172672626710
1600242671020000002669402516001010800008000010800008000050116888018840321526690267092670966533668916001020800008000020800008000026709267091180021109101080000100800001000502052071644267068000080000102671026798268212671926726
160024267092000000266942251600101080000800001080000800005011688801884032152669026709267096653366891600102080000800002080000800002670926709118002110910108000010080130388600502052041646267068000080000102690126779267162675926714
1600242670920001002669402516001010800008000010800008000050116888018840321526690267092670966533668916001020800008000020800008000026709267091180021109101080000100800002000502052031634267068000080000102686026724267112671326710
1600242671121900002669402516001010800008000010800008000050116888018840321526690267092670966533668916001020800008000020800008000026714267151180021109101080000100800000000502055041647267068000080000102671026887267682678826710
1600242670920000002669422516001010800008000010800008000050116888018840321526690267092670966533668916001020800008000020800008000026709267091180021109101080000100800000000502055041644267068000080000102671026847268182672126718
1600242670920000002669422516001010800008000010800008000050116888018840321526690267092670966533668916001020800008000020800008000026709267091180021109101080000100800003000502055041666267068000080000102680426888267152671826710
1600242670919900002669412516001010800008000010800008000050116888018840321526690267092670966533668916001020800008000020800008000026709267091180021109101080000100805230000502055071646267068000080000102671026710267102671026718
1600242671120000002669402516001010800008000010800008000050116888018840321526690267092670966533668916001020800008000020800008000026709267091180021109101080000100800003000502055031634267068000080000102671026805268312671626719