2017-08-02 08:28:10 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-- -mcpu=bdver1 | FileCheck %s
|
SHLD/SHRD are VectorPath (microcode) instructions known to have poor latency on certain architectures. While generating SHLD/SHRD instructions is acceptable when optimizing for size, optimizing for speed on these platforms should be implemented using alternative sequences of instructions composed of add, adc, shr, shl, or and lea which are directPath instructions. These alternative instructions not only have a lower latency but they also increase the decode bandwidth by allowing simultaneous decoding of a third directPath instruction.
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
2013-11-22 07:21:26 +08:00
|
|
|
|
|
|
|
; clang -Oz -c test1.cpp -emit-llvm -S -o
|
|
|
|
; Verify that we generate shld insruction when we are optimizing for size,
|
|
|
|
; even for X86_64 processors that are known to have poor latency double
|
2014-06-08 05:23:09 +08:00
|
|
|
; precision shift instructions.
|
SHLD/SHRD are VectorPath (microcode) instructions known to have poor latency on certain architectures. While generating SHLD/SHRD instructions is acceptable when optimizing for size, optimizing for speed on these platforms should be implemented using alternative sequences of instructions composed of add, adc, shr, shl, or and lea which are directPath instructions. These alternative instructions not only have a lower latency but they also increase the decode bandwidth by allowing simultaneous decoding of a third directPath instruction.
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
2013-11-22 07:21:26 +08:00
|
|
|
; uint64_t lshift10(uint64_t a, uint64_t b)
|
|
|
|
; {
|
|
|
|
; return (a << 10) | (b >> 54);
|
|
|
|
; }
|
|
|
|
|
2015-08-11 01:00:44 +08:00
|
|
|
; Function Attrs: minsize nounwind readnone uwtable
|
SHLD/SHRD are VectorPath (microcode) instructions known to have poor latency on certain architectures. While generating SHLD/SHRD instructions is acceptable when optimizing for size, optimizing for speed on these platforms should be implemented using alternative sequences of instructions composed of add, adc, shr, shl, or and lea which are directPath instructions. These alternative instructions not only have a lower latency but they also increase the decode bandwidth by allowing simultaneous decoding of a third directPath instruction.
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
2013-11-22 07:21:26 +08:00
|
|
|
define i64 @_Z8lshift10mm(i64 %a, i64 %b) #0 {
|
|
|
|
entry:
|
|
|
|
; CHECK: shldq $10
|
|
|
|
%shl = shl i64 %a, 10
|
|
|
|
%shr = lshr i64 %b, 54
|
|
|
|
%or = or i64 %shr, %shl
|
|
|
|
ret i64 %or
|
|
|
|
}
|
|
|
|
|
2015-08-11 01:00:44 +08:00
|
|
|
attributes #0 = { minsize nounwind readnone uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|
SHLD/SHRD are VectorPath (microcode) instructions known to have poor latency on certain architectures. While generating SHLD/SHRD instructions is acceptable when optimizing for size, optimizing for speed on these platforms should be implemented using alternative sequences of instructions composed of add, adc, shr, shl, or and lea which are directPath instructions. These alternative instructions not only have a lower latency but they also increase the decode bandwidth by allowing simultaneous decoding of a third directPath instruction.
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
2013-11-22 07:21:26 +08:00
|
|
|
|
|
|
|
|
|
|
|
; clang -Os -c test2.cpp -emit-llvm -S
|
|
|
|
; Verify that we generate shld insruction when we are optimizing for size,
|
|
|
|
; even for X86_64 processors that are known to have poor latency double
|
2014-06-08 05:23:09 +08:00
|
|
|
; precision shift instructions.
|
SHLD/SHRD are VectorPath (microcode) instructions known to have poor latency on certain architectures. While generating SHLD/SHRD instructions is acceptable when optimizing for size, optimizing for speed on these platforms should be implemented using alternative sequences of instructions composed of add, adc, shr, shl, or and lea which are directPath instructions. These alternative instructions not only have a lower latency but they also increase the decode bandwidth by allowing simultaneous decoding of a third directPath instruction.
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
2013-11-22 07:21:26 +08:00
|
|
|
; uint64_t lshift11(uint64_t a, uint64_t b)
|
|
|
|
; {
|
|
|
|
; return (a << 11) | (b >> 53);
|
|
|
|
; }
|
|
|
|
|
|
|
|
; Function Attrs: nounwind optsize readnone uwtable
|
|
|
|
define i64 @_Z8lshift11mm(i64 %a, i64 %b) #1 {
|
|
|
|
entry:
|
|
|
|
; CHECK: shldq $11
|
|
|
|
%shl = shl i64 %a, 11
|
|
|
|
%shr = lshr i64 %b, 53
|
|
|
|
%or = or i64 %shr, %shl
|
|
|
|
ret i64 %or
|
|
|
|
}
|
|
|
|
|
|
|
|
attributes #1 = { nounwind optsize readnone uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|
|
|
|
|
|
|
|
; clang -O2 -c test2.cpp -emit-llvm -S
|
|
|
|
; Verify that we do not generate shld insruction when we are not optimizing
|
|
|
|
; for size for X86_64 processors that are known to have poor latency double
|
2014-06-08 05:23:09 +08:00
|
|
|
; precision shift instructions.
|
SHLD/SHRD are VectorPath (microcode) instructions known to have poor latency on certain architectures. While generating SHLD/SHRD instructions is acceptable when optimizing for size, optimizing for speed on these platforms should be implemented using alternative sequences of instructions composed of add, adc, shr, shl, or and lea which are directPath instructions. These alternative instructions not only have a lower latency but they also increase the decode bandwidth by allowing simultaneous decoding of a third directPath instruction.
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
2013-11-22 07:21:26 +08:00
|
|
|
; uint64_t lshift12(uint64_t a, uint64_t b)
|
|
|
|
; {
|
|
|
|
; return (a << 12) | (b >> 52);
|
|
|
|
; }
|
|
|
|
|
|
|
|
; Function Attrs: nounwind optsize readnone uwtable
|
|
|
|
define i64 @_Z8lshift12mm(i64 %a, i64 %b) #2 {
|
|
|
|
entry:
|
|
|
|
; CHECK: shlq $12
|
|
|
|
; CHECK-NEXT: shrq $52
|
|
|
|
%shl = shl i64 %a, 12
|
|
|
|
%shr = lshr i64 %b, 52
|
|
|
|
%or = or i64 %shr, %shl
|
|
|
|
ret i64 %or
|
|
|
|
}
|
|
|
|
|
|
|
|
attributes #2= { nounwind readnone uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|
|
|
|
|