You've already forked linux-packaging-mono
75 lines
1.8 KiB
LLVM
75 lines
1.8 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=bdver1 | FileCheck %s
|
|
; Verify that for the architectures that are known to have poor latency
|
|
; double precision shift instructions we generate alternative sequence
|
|
; of instructions with lower latencies instead of shld instruction.
|
|
|
|
;uint64_t lshift1(uint64_t a, uint64_t b)
|
|
;{
|
|
; return (a << 1) | (b >> 63);
|
|
;}
|
|
|
|
; CHECK-LABEL: lshift1:
|
|
; CHECK: shrq $63, %rsi
|
|
; CHECK-NEXT: leaq (%rsi,%rdi,2), %rax
|
|
|
|
define i64 @lshift1(i64 %a, i64 %b) nounwind readnone uwtable {
|
|
entry:
|
|
%shl = shl i64 %a, 1
|
|
%shr = lshr i64 %b, 63
|
|
%or = or i64 %shr, %shl
|
|
ret i64 %or
|
|
}
|
|
|
|
;uint64_t lshift2(uint64_t a, uint64_t b)
|
|
;{
|
|
; return (a << 2) | (b >> 62);
|
|
;}
|
|
|
|
; CHECK-LABEL: lshift2:
|
|
; CHECK: shrq $62, %rsi
|
|
; CHECK-NEXT: leaq (%rsi,%rdi,4), %rax
|
|
|
|
define i64 @lshift2(i64 %a, i64 %b) nounwind readnone uwtable {
|
|
entry:
|
|
%shl = shl i64 %a, 2
|
|
%shr = lshr i64 %b, 62
|
|
%or = or i64 %shr, %shl
|
|
ret i64 %or
|
|
}
|
|
|
|
;uint64_t lshift7(uint64_t a, uint64_t b)
|
|
;{
|
|
; return (a << 7) | (b >> 57);
|
|
;}
|
|
|
|
; CHECK: lshift7:
|
|
; CHECK: shlq $7, {{.*}}
|
|
; CHECK-NEXT: shrq $57, {{.*}}
|
|
; CHECK-NEXT: leaq ({{.*}},{{.*}}), {{.*}}
|
|
|
|
define i64 @lshift7(i64 %a, i64 %b) nounwind readnone uwtable {
|
|
entry:
|
|
%shl = shl i64 %a, 7
|
|
%shr = lshr i64 %b, 57
|
|
%or = or i64 %shr, %shl
|
|
ret i64 %or
|
|
}
|
|
|
|
;uint64_t lshift63(uint64_t a, uint64_t b)
|
|
;{
|
|
; return (a << 63) | (b >> 1);
|
|
;}
|
|
|
|
; CHECK: lshift63:
|
|
; CHECK: shlq $63, {{.*}}
|
|
; CHECK-NEXT: shrq {{.*}}
|
|
; CHECK-NEXT: leaq ({{.*}},{{.*}}), {{.*}}
|
|
|
|
define i64 @lshift63(i64 %a, i64 %b) nounwind readnone uwtable {
|
|
entry:
|
|
%shl = shl i64 %a, 63
|
|
%shr = lshr i64 %b, 1
|
|
%or = or i64 %shr, %shl
|
|
ret i64 %or
|
|
}
|