On PowerPC targets, `half` uses the default legalization of promoting to a `f32`. However, this has some fundamental issues related to inability to round trip. Resolve this by switching to the soft legalization, which passes `f16` as an `i16`. The PowerPC ABI Specification does not define a `_Float16` type, so the calling convention changes are acceptable. Fixes the PowerPC part of https://github.com/llvm/llvm-project/issues/97975 Fixes the PowerPC part of https://github.com/llvm/llvm-project/issues/97981
28 lines
918 B
LLVM
28 lines
918 B
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mcpu=pwr8 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
|
|
; RUN: -mtriple=powerpc64le-unknown-unknown < %s | FileCheck %s
|
|
; RUN: llc -mcpu=pwr9 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
|
|
; RUN: -mtriple=powerpc64le-unknown-unknown < %s | FileCheck %s \
|
|
; RUN: -check-prefix=CHECK-P9
|
|
|
|
define dso_local half @test2(i64 %a, i64 %b) local_unnamed_addr #0 {
|
|
; CHECK-LABEL: test2:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: add r3, r4, r3
|
|
; CHECK-NEXT: addi r3, r3, 11
|
|
; CHECK-NEXT: blr
|
|
;
|
|
; CHECK-P9-LABEL: test2:
|
|
; CHECK-P9: # %bb.0: # %entry
|
|
; CHECK-P9-NEXT: add r3, r4, r3
|
|
; CHECK-P9-NEXT: addi r3, r3, 11
|
|
; CHECK-P9-NEXT: blr
|
|
entry:
|
|
%add = add i64 %b, %a
|
|
%0 = trunc i64 %add to i16
|
|
%conv = add i16 %0, 11
|
|
%call = bitcast i16 %conv to half
|
|
ret half %call
|
|
}
|
|
attributes #0 = { nounwind }
|