mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 03:33:20 +01:00
eda4e2e4a7
AMD's processors family K7, K8, K10, K12, K15 and K16 are known to have SHLD/SHRD instructions with very poor latency. Optimization guides for these processors recommend using an alternative sequence of instructions. For these AMD's processors, I disabled folding (or (x << c) | (y >> (64 - c))) when we are not optimizing for size. It might be beneficial to disable this folding for some of the Intel's processors. However, since I couldn't find specific recommendations regarding using SHLD/SHRD instructions on Intel's processors, I haven't disabled this peephole for Intel. llvm-svn: 195383
75 lines
1.8 KiB
LLVM
75 lines
1.8 KiB
LLVM
; RUN: llc < %s -march=x86-64 -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 shrd instruction.
|
|
|
|
;uint64_t rshift1(uint64_t a, uint64_t b)
|
|
;{
|
|
; return (a >> 1) | (b << 63);
|
|
;}
|
|
|
|
; CHECK: rshift1:
|
|
; CHECK: shrq {{.*}}
|
|
; CHECK-NEXT: shlq $63, {{.*}}
|
|
; CHECK-NEXT: leaq ({{.*}},{{.*}}), {{.*}}
|
|
|
|
define i64 @rshift1(i64 %a, i64 %b) nounwind readnone uwtable {
|
|
%1 = lshr i64 %a, 1
|
|
%2 = shl i64 %b, 63
|
|
%3 = or i64 %2, %1
|
|
ret i64 %3
|
|
}
|
|
|
|
;uint64_t rshift2(uint64_t a, uint64_t b)
|
|
;{
|
|
; return (a >> 2) | (b << 62);
|
|
;}
|
|
|
|
; CHECK: rshift2:
|
|
; CHECK: shrq $2, {{.*}}
|
|
; CHECK-NEXT: shlq $62, {{.*}}
|
|
; CHECK-NEXT: leaq ({{.*}},{{.*}}), {{.*}}
|
|
|
|
|
|
define i64 @rshift2(i64 %a, i64 %b) nounwind readnone uwtable {
|
|
%1 = lshr i64 %a, 2
|
|
%2 = shl i64 %b, 62
|
|
%3 = or i64 %2, %1
|
|
ret i64 %3
|
|
}
|
|
|
|
;uint64_t rshift7(uint64_t a, uint64_t b)
|
|
;{
|
|
; return (a >> 7) | (b << 57);
|
|
;}
|
|
|
|
; CHECK: rshift7:
|
|
; CHECK: shrq $7, {{.*}}
|
|
; CHECK-NEXT: shlq $57, {{.*}}
|
|
; CHECK-NEXT: leaq ({{.*}},{{.*}}), {{.*}}
|
|
|
|
|
|
define i64 @rshift7(i64 %a, i64 %b) nounwind readnone uwtable {
|
|
%1 = lshr i64 %a, 7
|
|
%2 = shl i64 %b, 57
|
|
%3 = or i64 %2, %1
|
|
ret i64 %3
|
|
}
|
|
|
|
;uint64_t rshift63(uint64_t a, uint64_t b)
|
|
;{
|
|
; return (a >> 63) | (b << 1);
|
|
;}
|
|
|
|
; CHECK: rshift63:
|
|
; CHECK: shrq $63, {{.*}}
|
|
; CHECK-NEXT: leaq ({{.*}},{{.*}}), {{.*}}
|
|
; CHECK-NEXT: orq {{.*}}, {{.*}}
|
|
|
|
define i64 @rshift63(i64 %a, i64 %b) nounwind readnone uwtable {
|
|
%1 = lshr i64 %a, 63
|
|
%2 = shl i64 %b, 1
|
|
%3 = or i64 %2, %1
|
|
ret i64 %3
|
|
}
|