Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMULH (scalar, H)

Test 1: uops

Code:

  sqrdmulh h0, h0, h1
  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)0318191e1f3a3f4e51inst 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)a0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000073416222630100030383038303830383038
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000073216222630100030383038303830383038
1004303723002400612548251000100010003983130301830373037241532895100010002000303730371110011000000073216222630100030383038303830383038
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000073216222630100030383038303830383038
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000073216222630100030383038303830383038
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000073216222630100030383038303830383038
100430372200000612548251000100010003983130301830373037241532895100010002000303730371110011000000073216222630100030383038303830383038
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000373216222630100030383038303830383038
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000073216222630100030383038303830383038
100430372201000612548251000100010003983130301830373037241532895100010002000303730371110011000000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrdmulh h0, h0, h1
  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)0305070a1e3f4e51inst 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)696b6d6edispatch 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)9fa8c2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250110127929548251010010010000100100005004277313300180300373003728272728740101002001000820020016300373003711102011009910010010000100001117181161129651100001003003830038300383003830038
10204300372240110125429548251010010010000106100005964277313300180300373003728272628741101002001000820020016300373003711102011009910010010000100001117171161129650100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
1020430037225000246129548251010010010000100100005004277313300180300613003728265328745101002001000020020000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)696b6d6edispatch 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)9fa6a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129539251001010100001010000504277313300180300373022728287328767100102010000202000030037300371110021109101010000100000640249222963010000103003830038301813003830038
10024301322250006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100000640216242963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313301620300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqrdmulh h0, h1, h0
  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)031e1f3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010003907101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372251350130295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa6a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000061295482510010101000010100005042773133001830037300372830232876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010002006403163629705010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037224000000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037224000000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqrdmulh h0, h8, h9
  sqrdmulh h1, h8, h9
  sqrdmulh h2, h8, h9
  sqrdmulh h3, h8, h9
  sqrdmulh h4, h8, h9
  sqrdmulh h5, h8, h9
  sqrdmulh h6, h8, h9
  sqrdmulh h7, h8, h9
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915100412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100030051101161120036800001002004020040200402004020040
802042003915000622580212100800001008000050064000002006320039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002010620040200402004020097
802042003915010412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042008915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100100051101161120036800001002004020040200402004020040
802042003915000692580100100800001008000050064000012002020039203479973399978010020080000200160000200392003911802011009910010080000100030051101161120036800001002004020040200402004020040
8020420039150012412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200912003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150012412580100100800001008000050064000002002020039200399981399978010020080000200160000200392003911802011009910010080000100000051101162120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040

1000 unrolls and 10 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)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)9fa0a8acc2c5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048185008225800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100132005020116112003680000102004020040200402004020040
8002420039185008225800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000102100005020116112003680000102004020040200402004020040
8002420039185004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100030005020116112003680000102004020040200402004020040
8002420039185004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000005020116112003680000102004020040200402004020040
800242003917401324025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000005020116112003680000102004020040200402004020040
8002420039173004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000005020116112003680000102004020040200402004020040
8002420039173004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000005020116112003680000102004020040200402004020040
8002420039174004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000005020116112003680000102004020040200402004020040
8002420039161004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000005020116112003680000102004020040200402004020040
8002420039160004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000005020116112003680000102004020040200402004020040