mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +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
58 lines
1.9 KiB
LLVM
58 lines
1.9 KiB
LLVM
; RUN: llc < %s -march=x86-64 -mcpu=athlon | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=athlon-tbird | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=athlon-4 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=athlon-xp | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=athlon-mp | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=k8 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=opteron | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=athlon64 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=athlon-fx | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=k8-sse3 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=opteron-sse3 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=athlon64-sse3 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=amdfam10 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=btver1 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=btver2 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=bdver1 | FileCheck %s
|
|
; RUN: llc < %s -march=x86-64 -mcpu=bdver2 | FileCheck %s
|
|
|
|
; Verify that for the X86_64 processors that are known to have poor latency
|
|
; double precision shift instructions we do not generate 'shld' or 'shrd'
|
|
; instructions.
|
|
|
|
;uint64_t lshift(uint64_t a, uint64_t b, int c)
|
|
;{
|
|
; return (a << c) | (b >> (64-c));
|
|
;}
|
|
|
|
define i64 @lshift(i64 %a, i64 %b, i32 %c) nounwind readnone {
|
|
entry:
|
|
; CHECK-NOT: shld
|
|
%sh_prom = zext i32 %c to i64
|
|
%shl = shl i64 %a, %sh_prom
|
|
%sub = sub nsw i32 64, %c
|
|
%sh_prom1 = zext i32 %sub to i64
|
|
%shr = lshr i64 %b, %sh_prom1
|
|
%or = or i64 %shr, %shl
|
|
ret i64 %or
|
|
}
|
|
|
|
;uint64_t rshift(uint64_t a, uint64_t b, int c)
|
|
;{
|
|
; return (a >> c) | (b << (64-c));
|
|
;}
|
|
|
|
define i64 @rshift(i64 %a, i64 %b, i32 %c) nounwind readnone {
|
|
entry:
|
|
; CHECK-NOT: shrd
|
|
%sh_prom = zext i32 %c to i64
|
|
%shr = lshr i64 %a, %sh_prom
|
|
%sub = sub nsw i32 64, %c
|
|
%sh_prom1 = zext i32 %sub to i64
|
|
%shl = shl i64 %b, %sh_prom1
|
|
%or = or i64 %shl, %shr
|
|
ret i64 %or
|
|
}
|
|
|
|
|