mirror of
https://github.com/RPCS3/llvm.git
synced 2025-05-23 13:56:06 +00:00
9f1fb82287
Summary: When promoting fp-to-uint16 to fp-to-sint32, the result is actually zero extended. For example, given double 65534.0, without legalization: fp-to-uint16: 65534.0 -> 0xfffe With the legalization: fp-to-sint32: 65534.0 -> 0x0000fffe Without this patch, legalization wrongly emits a signed extend assertion, which is consumed by later icmp instruction, and cause miscompile. Note that the floating point value must be in [0, 65535), otherwise the behavior is undefined. This patch reverts r279223 behavior and adds more tests and documentations. In PR29041's context, James Molloy mentioned that: We don't need to mask because conversion from float->uint8_t is undefined if the integer part of the float value is not representable in uint8_t. Therefore we can assume this doesn't happen! which is totally true and good, because fptoui is documented clearly to have undefined behavior when overflow/underflow happens. We should take the advantage of this behavior so that we can save unnecessary mask instructions. Reviewers: jmolloy, nadav, echristo, kbarton Subscribers: mehdi_amini, nemanjai, llvm-commits Differential Revision: https://reviews.llvm.org/D28284 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@291015 91177308-0d34-0410-b5e6-96231b3b80d8
22 lines
589 B
LLVM
22 lines
589 B
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -O0 < %s | FileCheck %s
|
|
target triple = "powerpc64le--linux-gnu"
|
|
|
|
define i1 @Test(double %a) {
|
|
; CHECK-LABEL: Test:
|
|
; CHECK: # BB#0: # %entry
|
|
; CHECK-NEXT: xscvdpsxws 1, 1
|
|
; CHECK-NEXT: mfvsrwz 3, 1
|
|
; CHECK-NEXT: xori 3, 3, 65534
|
|
; CHECK-NEXT: cntlzw 3, 3
|
|
; CHECK-NEXT: srwi 3, 3, 5
|
|
; CHECK-NEXT: # implicit-def: %X4
|
|
; CHECK-NEXT: mr 4, 3
|
|
; CHECK-NEXT: mr 3, 4
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%conv = fptoui double %a to i16
|
|
%cmp = icmp eq i16 %conv, -2
|
|
ret i1 %cmp
|
|
}
|