Apple M1 Microarchitecture Research by Dougall Johnson

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

SCVTF (scalar, fixed-point, H from W)

Test 1: uops

Code:

  scvtf h0, w0, #3
  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)031e3f51inst 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)a6cfd5d6ddinst fetch restart (de)e0ld/st retires (ed)? fp/simd (ee)f5f6f7f8fd
2004376363612520001000100010001000140752282013573763767231092000100010001000100037637611100110001000731161137310001000377377377377377
2004376303612520001000100010001000140752282013573763767231092000100010001000100037637611100110001000731161137310001000377377377377377
2004376303612520001000100010001000140752282013573763767231092000100010001000100037637611100110001000731161137310001000377377377377377
2004376303612520001000100010001000140752282013573763767231092000100010001000100037637611100110001000731161137610001000377377377377377
2004376303612520001000100010001000140752282013573763767231092000100010001000100037637711100110001000731161137310001000377377377377377
2004376303612520001000100010001000140752282013573763767231092000100010001000100037937611100110001000731161137310001000377377377377377
2004376303612520001000100010001000140752282013573763767231092000100010001000100037637611100110001000731161137310001000377377377377377
2004376303612520001000100010001000140752282013573763767231092000100010001000100037637611100110001000731161137310001000377377377377377
2004376303612520001000100010001000140752282003573763767231092000100010001000100037637611100110001000731161137310001000377377377377377
2004376303612520001000100010001000140752282013573763767231092000100010001000100037637611100110001000731161137310001000377377377377377

Test 2: Latency 1->2 roundtrip

Code:

  scvtf h0, w0, #3
  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)03191e1f3f4f51inst 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)696d6edispatch 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)9fa6a8a9acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
3020413003297400013001911940825401001010020000100001002000010000500621454514802709130013130032130032125473712623630100200100032000520010003200051300341300321120201100991001010010000100100001021111131702161112953010000100001000010100130035130033130033130034130033
302041300339740180881300171194102540100101002000010000100200001000050062144971480270913001413003213003212545831262403010020010000200002001000020000130034130033112020110099100101001000010010000103000131012162212951910000100001000010100130033130033130034130036130036
3020413003297401201300191194082540100101002000010000100200001005050062144971480270913001313003213003212546631262443010020010000200002001000020000130034130035112020110099100101001000010010000103000131012162212951910000100001000010100130033130033130034130037130033
3020413003297401201300171194082540100101002000010000100200001000050062144971480270913001313003413003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000100000131012162312951910000100001000010100130033130033130033130033130033
3020413003297401201300171194082540100101002000010000100200001000050062145451480508213001613003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000103000131012162212951910000100001000010100130033130034130033130033130033
3020413003297301201300201194082540100101002000010000100200001000050062145931480270913001413003513003212546631262403010020010000200002001000020000130033130032112020110099100101001000010010000103000131012162212951910000100001000010100130033130033130033130033130033
302041300329740001300171194092540100101002000010000100200001000050062145451480282313001613003213003212546731262433010020010000200002001000020000130032130032112020110099100101001000010010000003000131012162212952010000100001000010100130033130033130033130036130034
3020413003297401201300171194082540100101002000010000100200001000050062146411480270913001313003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000103001131012162212952110000100001000010100130033130033130033130033130033
302041300329740001300171194082540100101002000010000100200001000050062145451481005913001313003213003212546631262403010020010000200002001000020000130032130033112020110099100101001000010010000100000131012162212951910000100001000010100130033130034130033130033130033
3020413003397401201300171194082540100101002000010000100200001000050062144971480282113001313003513003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000103000131012162212957310000100001000010100130033130036130034130033130033

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0032

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)9fa1a6a8acc2cfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
3002413003297500000120013001711944625400101001020000100001020113101968362620291493656501303850130034130034125492312626230010201055221466201024321222131026130949112002110910100101000010210059017111501772427303213146510043100001000010010132303132387132565132046132410
30024132454989100302439932552113245812049863640204100532007210060132268211421556269301149617700132150013210613242012654319012776234816241214723400261207523523132869132621351200211091010010100001041005511271030127011601112951910000100001000010010130035130033130033130033130033
3002413003297400000120013002011940925400101001020000100001020000100005062144971480052801300130130032130032125567312626230176201000020000201000020000130032130034112002110910100101000010010000130127011601112951910002100001000010010130033130035130034130033130036
3002413003297400100420013001711948125400191001120006100021020000100005062144971480064101300130130032130035125552312626230010201000020000201000020000130032130034112002110910100101000010010000030127011601112951910000100001000010010130033130034130033130033130033
3002413003297400000360013001711940825400101001020000100001020000100005062145451480097801300130130032130032125489312626230010201000020000201000020000130032130032112002110910100101000010010000030127011601112951910000100001000010010130088130034130033130036130033
300241300329740000000013001711940925400101001020000100001020000100005062144971480052801300150130032130033125489312626230010201000020000201000020000130032130032112002110910100101000010010000130127011601112951910000100001000010010130033130034130036130034130033
3002413013197400000120013001711941025400101001020000100001020000100005062145451480064111300130130041130034125489312626330010201000020000201000020000130032130035112002110910100101000010010000330127021611112951910000100001000010010130034130035130033130033130033
3002413003297400000120013001711940825400101001020000100001020000100005062144971480052801300140130032130032125489312626230177201000020000201000020000130032130032112002110910100101000010010000000127011601112951910000100001000010010130033130034130034130033130033
3002413003297400000450013001711940825400101001020000100001020000100005062144971480052801300130130032130033125489312626230010201000020000201000020000130032130032112002110910100101000010010000800127011601112951910000100001000010010130033130033130040130033130034
3002413003297400000120013001711940825400101001020000100001020000100005062144971480075601300130130032130032125489312626230010201000020000201000020000130032130032112002110910100101000010010000130127011601112951910000100001000010010130033130034130033130033130033

Test 3: throughput

Count: 8

Code:

  scvtf h0, w8, #3
  scvtf h1, w8, #3
  scvtf h2, w8, #3
  scvtf h3, w8, #3
  scvtf h4, w8, #3
  scvtf h5, w8, #3
  scvtf h6, w8, #3
  scvtf h7, w8, #3
  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)031e3f4f51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd6dde0ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042671220002670902516010010080000800001008002080015500116895118841631266902670926709663225680316013620080020800202008002080020267092670911802011009910010080000100800000011151171602670680000800001002671026710267102671026710
160204267092000267010251601001008000080000100800208001550011689511884163126690267092670966326665816013520080020800202008002080020267092670911802011009910010080000100800000011151171602670680000800001002671026710267102671026710
160204267092000267040251601001008000080000100800208001550011689511884163126690267092670966326665816013520080020800202008002080020267112670921802011009910010080000100800000011151171602670680000800001002671026710267102671026710
160204267092000266980251601001008000080000100800208001550011689511884163126690267092670966326665816013520080020800202008002080020267102670911802011009910010080000100800000011151171602670680000800001002671026710267102671026710
160204267092000269160251601001008000080000100800208001550011689511884163126690267092670966326665816013520080020800202008002080020267092670911802011009910010080000100800000011151171602670680000800001002671026710267102671026710
1602042670920002695902516010010080000800001008002080015500116895118841631266902670926709663243666916014120080020800202008002080020267092670911802011009910010080000100800000011151171602670680000800001002671026710267102671026710
160204267092000267050251601001008000080000100800208001550011689511884163126690267092670966566665816013520080020800202008002080020267092670911802011009910010080000100800000011151171602670680000800001002671026710267102671026710
160204267092000267000251601001008000080000100800208001550011689511884163126690267092670966326665816013520080020800202008002080020267092670911802011009910010080000100800000011151171602670680000800001002671026710267102671026710
160204267092000267070251601001008000080000100800208001550011689511884163126690267092671166326665816013520080020800202008002080020267092670911802011009910010080000100800000011151171602670680000800001002671026710267102671026710
160204267092000266940251601001008000080000100800208001550011689511884163126690267092670966326665816013520080020800202008002080020267092670911802011009910010080000100800001011151171602670680000800001002671026710267102671026710

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f4f51inst 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)9fa6a8accfd0d2d5d6ddinst fetch restart (de)e0ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242688121712267012251600101080000800001080000800005011719211884032102669026709267136657366931600102080000800002080000800002671426713118002110910108000010800000050200018162314267118000080000102671426714267102671426710
160024267132000267070251600101080000800001080000800005011688801884032002669426714267096657366931600102080000800002080000800002671326714118002110910108000010800000350200023161623267108000080000102671426714267142671426714
1600242671320012267080251600101080000800001080000800005011744791884013002669026709267146653366931600102080000800002080000800002671326710118002110910108000010800001350200018162217267108000080000102671026714267142671426714
1600242671420012267282251600101080000800001080000800005011689401884015102669426713267136657366931600102080000800002080000800002671526713118002110910108000010800000350200022162323267068000080000102671026714267142671426710
1600242670920012267073251600101080000800001080000800005011681531882520102669026714267096653366901600102080000800002080000800002690426726118002110910108000010800001050200022162223267068000080000102671026711267142671426710
1600242671319912267223251600101080000800001080000800005011682581884727102669426713267126657366931600102080000800002080000800002671326713118002110910108000010800000350200023161422267068000080000102671426714267172671726714
1600242671420012267243251600101080000800001080000800005011681021884032102669426709267136653366891600102080000800002080000800002670926714118002110910108000010800001050200017162217267068000080000102671026714267102671426714
1600242671320012267102251600101080000800001080000800005011816181887607102669426709267096656366931600102080000800002080000800002670926709118002110910108000010800001350860023161722267228000080000102671426714267142671026710
1600242671320012267032251600101080000800001080000800005011686341883468102669426713267146656366891600102080000800002080000800002670926709118002110910108000010800000350200022162323267068000080000102671026710267142671526714
160024267092000267060251600101080000800001080000800005011695331884568102669426714267136657366931600102080000801922080000800002672726713118002110910108000010800001050430013162218267108000080000102671427306267182671526715