maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][Btver2] Add correct mul/imul schedule costs 

Integer multiply is performed on the JMul function unit and i64 requires double pumping

llvm-svn: 327707
This commit is contained in:
Simon Pilgrim 2018-03-16 14:01:01 +00:00
parent 8d28ae6aec
commit 23578e7d3c
2 changed files with 18 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
llvm/lib/Target/X86/X86ScheduleBtVer2.td
View File

@ -117,7 +117,7 @@ def : WriteRes<WriteRMW, [JSAGU]>;
////////////////////////////////////////////////////////////////////////////////
defm : JWriteResIntPair<WriteALU, [JALU01], 1>;
defm : JWriteResIntPair<WriteIMul, [JALU1], 3>;
defm : JWriteResIntPair<WriteIMul, [JALU1, JMul], 3, [1, 1], 2>; // i8/i16/i32 multiplication
defm : JWriteResIntPair<WriteIDiv, [JALU1, JDiv], 41, [1, 41], 2>; // Worst case (i64 division)
def : WriteRes<WriteIMulH, [JALU1]> {
@ -152,6 +152,19 @@ def JWriteTZCNTLd : SchedWriteRes<[JLAGU, JALU01]> {
def : InstRW<[JWriteTZCNT], (instrs TZCNT16rr, TZCNT32rr, TZCNT64rr)>;
def : InstRW<[JWriteTZCNTLd], (instrs TZCNT16rm, TZCNT32rm, TZCNT64rm)>;
def JWriteIMul64 : SchedWriteRes<[JALU1, JMul]> {
let Latency = 6;
let ResourceCycles = [1, 4];
let NumMicroOps = 2;
}
def JWriteIMul64Ld : SchedWriteRes<[JLAGU, JALU1, JMul]> {
let Latency = 9;
let ResourceCycles = [1, 1, 4];
let NumMicroOps = 2;
}
def : InstRW<[JWriteIMul64], (instrs MUL64r, IMUL64r)>;
def : InstRW<[JWriteIMul64Ld], (instrs MUL64m, IMUL64m)>;
def JWriteIDiv8 : SchedWriteRes<[JALU1, JDiv]> {
let Latency = 12;
let ResourceCycles = [1, 12];

8
llvm/test/CodeGen/X86/schedule-x86_64.ll
View File

@ -6078,8 +6078,8 @@ define void @test_imul_64(i64 %a0, i64* %a1) optsize {
; BTVER2-LABEL: test_imul_64:
; BTVER2: # %bb.0:
; BTVER2-NEXT: #APP
; BTVER2-NEXT: imulq %rdi # sched: [3:1.00]
; BTVER2-NEXT: imulq (%rsi) # sched: [6:1.00]
; BTVER2-NEXT: imulq %rdi # sched: [6:4.00]
; BTVER2-NEXT: imulq (%rsi) # sched: [9:4.00]
; BTVER2-NEXT: imulq %rdi, %rdi # sched: [3:1.00]
; BTVER2-NEXT: imulq (%rsi), %rdi # sched: [6:1.00]
; BTVER2-NEXT: imulq $665536, %rdi, %rdi # imm = 0xA27C0
@ -8093,8 +8093,8 @@ define void @test_mul(i8 %a0, i16 %a1, i32 %a2, i64 %a3, i8 *%p0, i16 *%p1, i32
; BTVER2-NEXT: mulw (%r9) # sched: [6:1.00]
; BTVER2-NEXT: mull %edx # sched: [3:1.00]
; BTVER2-NEXT: mull (%rax) # sched: [6:1.00]
; BTVER2-NEXT: mulq %rcx # sched: [3:1.00]
; BTVER2-NEXT: mulq (%r10) # sched: [6:1.00]
; BTVER2-NEXT: mulq %rcx # sched: [6:4.00]
; BTVER2-NEXT: mulq (%r10) # sched: [9:4.00]
; BTVER2-NEXT: #NO_APP
; BTVER2-NEXT: retq # sched: [4:1.00]
;