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, D from D)

Test 1: uops

Code:

  ucvtf d0, d0
  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)03091e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100430372300842547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724001032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723001472547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724012612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400822547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400842547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400752547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf d0, d0
  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)03080b1e3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300607682954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300841110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372330036612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372320069612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372320027612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000037101161129633100001003003830038300383003830038
10204300372320027612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723300393612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372330001032954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300863003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723300135612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723300301442954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000037101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070a1e3a3f4e51inst 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)9fa8accfd2d5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372251102682954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006440121612729629010000103003830038300383003830038
100243003722511122962954725100101010000101000050427716003001830037300372828632876710010201018020100003003730037111002110910101000010106440111661129629010000103003830038300383003830038
100243003722511026829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100064401116121229629010000103003830038300383003830038
10024300372251102682954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006440111611629629010000103003830038300383003830038
100243003722511026829547251001010100001010000504277160030018300373003728275328767100102010000201000030037300371110021109101010000100064401116111129629010000103003830038300383003830038
10024300372241102892954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006440111661129629010000103003830038300383003830038
1002430037224110217729547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100964401216111129629010000103003830038300383003830038
10024300372241102682954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006440616111129629010000103003830038300383003830038
100243003722411026829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100064401116121129629010000103003830038300383003830038
100243003722511026829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000103064401116111129629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf d0, d8
  ucvtf d1, d8
  ucvtf d2, d8
  ucvtf d3, d8
  ucvtf d4, d8
  ucvtf d5, d8
  ucvtf d6, d8
  ucvtf d7, d8
  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)031e3f51inst 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)5e6061696d6edispatch 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)9fa0a8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815503025801081008000810080020500640132014200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801160020036800001002004020040200402004020040
8020420039155052625801081008000810080020500640132004200202003920039997769990801202008003220080032200392003911802011009910010080000100003111511840160020036800001002004020040200402004020040
8020420039155051258010810080008100800205006401320102002020039200399977699908012020080032200800322003920039118020110099100100800001004533111511840160020036800001002004020040200402004020040
802042003915507225801081008000810080020500640132010200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511840160020036800001002004020040200402004020040
802042003915603025801081008000810080020500640132004200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511800160020036800001002004020040200402004020040
8020420039156030258010810080008100800205006401320102002020039200399977699908012020080032200800322003920039118020110099100100800001000087111511840160020036800001002004020040200402004020040
802042003915603025801081008000810080020500640132004200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511800160020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132004200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511840160020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132004200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511800160020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132010200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511840160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)91inst b.cc (94)inst int store (96)inst integer (97)inst neon or fp (9a)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511559450258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110901001080000100000502010166172003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090100108000010001350208161762003680000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109010010800001000039502017161462003680000102004020040200402004020040
80024200391550682580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109010010800001000005020171617172003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090100108000010000050208168172003680000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109010010800001000005020181617172003680000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109010010800001000005020121617172003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090100108000010000050208161772003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090100108000010000050206161762003680000102004020040200402004020040
800242003915504622580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109010010800001000005020171617172003680000102004020040200402004020040