1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Craig Topper 7d16c968d5 [X86] Rework the "sahf" feature flag to only apply to 64-bit mode.
SAHF/LAHF instructions are always available in 32-bit mode. Early
64-bit capable CPUs made the undefined opcodes in 64-bit mode. This
was changed on later CPUs.

We have a feature flag to control our usage of these instructions.
This feature flag is hooked up to a clang command line option
-msahf/-mno-sahf specifically to give control of the 64-bit mode
behavior.

In the backend X86Subtarget constructor we were explicitly forcing
+sahf into the feature flag string if we were not compiling for
64-bit mode. This was intended to make the predicates always allow
the instructions outside of 64-bit mode. Unfortunately, the way
it was placed into the string allowed -mno-sahf from clang to disable
SAHF instructions in 32-bit mode. This causes an assertion to fire
if you compile a floating point comparison with something like
"-march=pentium -mno-sahf" as our floating point comparison
handling on CPUs that don't support FCOMI/FUCOMI instructions
requires SAHF.

To fix this, this commit restricts the feature flag to only apply to
64-bit mode by ignoring the flag outside 64-bit mode in
X86Subtarget::hasLAHFSAHF(). This way we don't need to mess with
the feature string at all.
2020-07-22 16:57:46 -07:00

34 lines
1.2 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-- | FileCheck %s
; Sanity check that we ignore -sahf in 32-bit mode rather than asserting.
; RUN: llc < %s -mtriple=i686-- -mattr=-sahf | FileCheck %s
declare i1 @llvm.isunordered.f32(float, float)
define float @cmp(float %A, float %B, float %C, float %D) nounwind {
; CHECK-LABEL: cmp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: flds {{[0-9]+}}(%esp)
; CHECK-NEXT: flds {{[0-9]+}}(%esp)
; CHECK-NEXT: fucompp
; CHECK-NEXT: fnstsw %ax
; CHECK-NEXT: # kill: def $ah killed $ah killed $ax
; CHECK-NEXT: sahf
; CHECK-NEXT: jbe .LBB0_1
; CHECK-NEXT: # %bb.2: # %entry
; CHECK-NEXT: leal {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: flds (%eax)
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB0_1:
; CHECK-NEXT: leal {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: flds (%eax)
; CHECK-NEXT: retl
entry:
%tmp.1 = fcmp uno float %A, %B ; <i1> [#uses=1]
%tmp.2 = fcmp oge float %A, %B ; <i1> [#uses=1]
%tmp.3 = or i1 %tmp.1, %tmp.2 ; <i1> [#uses=1]
%tmp.4 = select i1 %tmp.3, float %C, float %D ; <float> [#uses=1]
ret float %tmp.4
}