maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/pr34149.ll

37 lines
1.2 KiB
LLVM
Raw Normal View History

[X86] Adding a test point for PR34149 'Suboptimal codegen for "fast" minnum and maxnum' Differential Revision: https://reviews.llvm.org/D37614 llvm-svn: 312778
2017-09-08 17:15:36 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=haswell | FileCheck %s
declare <4 x double> @llvm.minnum.v4f64(<4 x double> %x, <4 x double> %y)
declare <4 x double> @llvm.maxnum.v4f64(<4 x double> %x, <4 x double> %y)
define <4 x double> @via_minnum(<4 x double> %x, <4 x double> %y) {
; CHECK-LABEL: via_minnum:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[DAG] propagate FMF for all FPMathOperators This is a simple hack based on what's proposed in D37686, but we can extend it if needed in follow-ups. It gets us most of the FMF functionality that we want without adding any state bits to the flags. It also intentionally leaves out non-FMF flags (nsw, etc) to minimize the patch. It should provide a superset of the functionality from D46563 - the extra tests show propagation and codegen diffs for fcmp, vecreduce, and FP libcalls. The PPC log2() test shows the limits of this most basic approach - we only applied 'afn' to the last node created for the call. AFAIK, there aren't any libcall optimizations based on the flags currently, so that shouldn't make any difference. Differential Revision: https://reviews.llvm.org/D46854 llvm-svn: 332358
2018-05-15 22:16:24 +08:00
; CHECK-NEXT: vminpd %ymm1, %ymm0, %ymm0
[X86] Adding a test point for PR34149 'Suboptimal codegen for "fast" minnum and maxnum' Differential Revision: https://reviews.llvm.org/D37614 llvm-svn: 312778
2017-09-08 17:15:36 +08:00
; CHECK-NEXT: retq
%z = call fast <4 x double> @llvm.minnum.v4f64(<4 x double> %x, <4 x double> %y) readnone
ret <4 x double> %z
}
define <4 x double> @via_maxnum(<4 x double> %x, <4 x double> %y) {
; CHECK-LABEL: via_maxnum:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[DAG] propagate FMF for all FPMathOperators This is a simple hack based on what's proposed in D37686, but we can extend it if needed in follow-ups. It gets us most of the FMF functionality that we want without adding any state bits to the flags. It also intentionally leaves out non-FMF flags (nsw, etc) to minimize the patch. It should provide a superset of the functionality from D46563 - the extra tests show propagation and codegen diffs for fcmp, vecreduce, and FP libcalls. The PPC log2() test shows the limits of this most basic approach - we only applied 'afn' to the last node created for the call. AFAIK, there aren't any libcall optimizations based on the flags currently, so that shouldn't make any difference. Differential Revision: https://reviews.llvm.org/D46854 llvm-svn: 332358
2018-05-15 22:16:24 +08:00
; CHECK-NEXT: vmaxpd %ymm1, %ymm0, %ymm0
[X86] Adding a test point for PR34149 'Suboptimal codegen for "fast" minnum and maxnum' Differential Revision: https://reviews.llvm.org/D37614 llvm-svn: 312778
2017-09-08 17:15:36 +08:00
; CHECK-NEXT: retq
%z = call fast <4 x double> @llvm.maxnum.v4f64(<4 x double> %x, <4 x double> %y) readnone
ret <4 x double> %z
}
define <4 x double> @via_fcmp(<4 x double> %x, <4 x double> %y) {
; CHECK-LABEL: via_fcmp:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[X86] Adding a test point for PR34149 'Suboptimal codegen for "fast" minnum and maxnum' Differential Revision: https://reviews.llvm.org/D37614 llvm-svn: 312778
2017-09-08 17:15:36 +08:00
; CHECK-NEXT: vminpd %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
%c = fcmp ule <4 x double> %x, %y
%z = select <4 x i1> %c, <4 x double> %x, <4 x double> %y
ret <4 x double> %z
}