mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
8a40b05b65
Summary: During legalization if i16, do not ASSERTZEXT the result of FP_TO_FP16. Directly return an FP_TO_FP16 node with return type as the promote-to-type of i16. This patch also removes extraneous length check. This legalization should be valid even if integer and float types are of different lengths. This patch breaks a hard-float test for fp16 args. The test is changed to allow a vmov to zero-out the top bits, and also ensure that the return value is in an FP register. Reviewers: ab, jmolloy Subscribers: srhines, llvm-commits Differential Revision: http://reviews.llvm.org/D15438 llvm-svn: 257184
42 lines
1.5 KiB
LLVM
42 lines
1.5 KiB
LLVM
; RUN: llc -float-abi soft -mattr=+fp16 < %s | FileCheck %s --check-prefix=CHECK --check-prefix=SOFT
|
|
; RUN: llc -float-abi hard -mattr=+fp16 < %s | FileCheck %s --check-prefix=CHECK --check-prefix=HARD
|
|
|
|
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
|
|
target triple = "armv7a--none-eabi"
|
|
|
|
define float @foo(float %a.coerce, float %b.coerce) {
|
|
entry:
|
|
%0 = bitcast float %a.coerce to i32
|
|
%tmp.0.extract.trunc = trunc i32 %0 to i16
|
|
%1 = bitcast i16 %tmp.0.extract.trunc to half
|
|
%2 = bitcast float %b.coerce to i32
|
|
%tmp1.0.extract.trunc = trunc i32 %2 to i16
|
|
%3 = bitcast i16 %tmp1.0.extract.trunc to half
|
|
%4 = fadd half %1, %3
|
|
%5 = bitcast half %4 to i16
|
|
%tmp5.0.insert.ext = zext i16 %5 to i32
|
|
%6 = bitcast i32 %tmp5.0.insert.ext to float
|
|
ret float %6
|
|
; CHECK: foo:
|
|
|
|
; SOFT: vmov {{s[0-9]+}}, r1
|
|
; SOFT: vmov {{s[0-9]+}}, r0
|
|
; SOFT: vcvtb.f32.f16 {{s[0-9]+}}, {{s[0-9]+}}
|
|
; SOFT: vcvtb.f32.f16 {{s[0-9]+}}, {{s[0-9]+}}
|
|
; SOFT: vadd.f32 {{s[0-9]+}}, {{s[0-9]+}}, {{s[0-9]+}}
|
|
; SOFT: vcvtb.f16.f32 {{s[0-9]+}}, {{s[0-9]+}}
|
|
; SOFT: vmov r0, {{s[0-9]+}}
|
|
|
|
; HARD-NOT: vmov
|
|
; HARD-NOT: uxth
|
|
; HARD: vcvtb.f32.f16 {{s[0-9]+}}, s1
|
|
; HARD: vcvtb.f32.f16 {{s[0-9]+}}, s0
|
|
; HARD: vadd.f32 {{s[0-9]+}}, {{s[0-9]+}}, {{s[0-9]+}}
|
|
; HARD: vcvtb.f16.f32 [[SREG:s[0-9]+]], {{s[0-9]+}}
|
|
; HARD-NEXT: vmov [[REG0:r[0-9]+]], [[SREG]]
|
|
; HARD-NEXT: uxth [[REG1:r[0-9]+]], [[REG0]]
|
|
; HARD-NEXT: vmov s0, [[REG1]]
|
|
|
|
; CHECK: bx lr
|
|
}
|