mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-22 09:29:31 +00:00
3f05a5e0ad
Other f64 opcodes not supported on SI can be lowered in a similar way. v2: use complex VOP3 patterns git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@233076 91177308-0d34-0410-b5e6-96231b3b80d8
61 lines
3.4 KiB
LLVM
61 lines
3.4 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=FUNC %s
|
|
|
|
declare double @llvm.fabs.f64(double %Val)
|
|
declare double @llvm.AMDGPU.fract.f64(double) nounwind readnone
|
|
|
|
; FUNC-LABEL: {{^}}fract_f64:
|
|
; GCN: v_fract_f64_e32 [[FRC:v\[[0-9]+:[0-9]+\]]], v{{\[}}[[LO:[0-9]+]]:[[HI:[0-9]+]]]
|
|
; SI: v_mov_b32_e32 v[[UPLO:[0-9]+]], -1
|
|
; SI: v_mov_b32_e32 v[[UPHI:[0-9]+]], 0x3fefffff
|
|
; SI: v_min_f64 v{{\[}}[[MINLO:[0-9]+]]:[[MINHI:[0-9]+]]], v{{\[}}[[UPLO]]:[[UPHI]]], [[FRC]]
|
|
; SI: v_cmp_class_f64_e64 [[COND:s\[[0-9]+:[0-9]+\]]], v{{\[}}[[LO]]:[[HI]]], 3
|
|
; SI: v_cndmask_b32_e64 v[[RESLO:[0-9]+]], v[[LO]], v[[MINLO]], [[COND]]
|
|
; SI: v_cndmask_b32_e64 v[[RESHI:[0-9]+]], v[[HI]], v[[MINHI]], [[COND]]
|
|
; SI: buffer_store_dwordx2 v{{\[}}[[RESLO]]:[[RESHI]]]
|
|
; CI: buffer_store_dwordx2 [[FRC]]
|
|
define void @fract_f64(double addrspace(1)* %out, double addrspace(1)* %src) nounwind {
|
|
%val = load double, double addrspace(1)* %src, align 4
|
|
%fract = call double @llvm.AMDGPU.fract.f64(double %val) nounwind readnone
|
|
store double %fract, double addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fract_f64_neg:
|
|
; GCN: v_fract_f64_e64 [[FRC:v\[[0-9]+:[0-9]+\]]], -v{{\[}}[[LO:[0-9]+]]:[[HI:[0-9]+]]]
|
|
; SI: v_mov_b32_e32 v[[UPLO:[0-9]+]], -1
|
|
; SI: v_mov_b32_e32 v[[UPHI:[0-9]+]], 0x3fefffff
|
|
; SI: v_min_f64 v{{\[}}[[MINLO:[0-9]+]]:[[MINHI:[0-9]+]]], v{{\[}}[[UPLO]]:[[UPHI]]], [[FRC]]
|
|
; SI: v_cmp_class_f64_e64 [[COND:s\[[0-9]+:[0-9]+\]]], v{{\[}}[[LO]]:[[HI]]], 3
|
|
; SI: v_cndmask_b32_e64 v[[RESLO:[0-9]+]], v[[LO]], v[[MINLO]], [[COND]]
|
|
; SI: v_cndmask_b32_e64 v[[RESHI:[0-9]+]], v[[HI]], v[[MINHI]], [[COND]]
|
|
; SI: buffer_store_dwordx2 v{{\[}}[[RESLO]]:[[RESHI]]]
|
|
; CI: buffer_store_dwordx2 [[FRC]]
|
|
define void @fract_f64_neg(double addrspace(1)* %out, double addrspace(1)* %src) nounwind {
|
|
%val = load double, double addrspace(1)* %src, align 4
|
|
%neg = fsub double 0.0, %val
|
|
%fract = call double @llvm.AMDGPU.fract.f64(double %neg) nounwind readnone
|
|
store double %fract, double addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fract_f64_neg_abs:
|
|
; GCN: v_fract_f64_e64 [[FRC:v\[[0-9]+:[0-9]+\]]], -|v{{\[}}[[LO:[0-9]+]]:[[HI:[0-9]+]]]|
|
|
; SI: v_mov_b32_e32 v[[UPLO:[0-9]+]], -1
|
|
; SI: v_mov_b32_e32 v[[UPHI:[0-9]+]], 0x3fefffff
|
|
; SI: v_min_f64 v{{\[}}[[MINLO:[0-9]+]]:[[MINHI:[0-9]+]]], v{{\[}}[[UPLO]]:[[UPHI]]], [[FRC]]
|
|
; SI: v_cmp_class_f64_e64 [[COND:s\[[0-9]+:[0-9]+\]]], v{{\[}}[[LO]]:[[HI]]], 3
|
|
; SI: v_cndmask_b32_e64 v[[RESLO:[0-9]+]], v[[LO]], v[[MINLO]], [[COND]]
|
|
; SI: v_cndmask_b32_e64 v[[RESHI:[0-9]+]], v[[HI]], v[[MINHI]], [[COND]]
|
|
; SI: buffer_store_dwordx2 v{{\[}}[[RESLO]]:[[RESHI]]]
|
|
; CI: buffer_store_dwordx2 [[FRC]]
|
|
define void @fract_f64_neg_abs(double addrspace(1)* %out, double addrspace(1)* %src) nounwind {
|
|
%val = load double, double addrspace(1)* %src, align 4
|
|
%abs = call double @llvm.fabs.f64(double %val)
|
|
%neg = fsub double 0.0, %abs
|
|
%fract = call double @llvm.AMDGPU.fract.f64(double %neg) nounwind readnone
|
|
store double %fract, double addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|