mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-10 06:25:01 +00:00
85dd075020
This basic combine was surprisingly missing. AMDGPU legalizes many operations in terms of 32-bit vector components, so not doing this results in many extra copies and subregister extracts that need to be cleaned up later. InstCombine already does this for the hasOneUse case. The target hook is to fix a handful of tests which break (e.g. ARM/vmov.ll) which turn from a vector materialize repeated immediate instruction to a constant vector load with more scalar copies from it. llvm-svn: 250129
106 lines
3.4 KiB
LLVM
106 lines
3.4 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
|
|
declare double @llvm.ceil.f64(double) nounwind readnone
|
|
declare <2 x double> @llvm.ceil.v2f64(<2 x double>) nounwind readnone
|
|
declare <3 x double> @llvm.ceil.v3f64(<3 x double>) nounwind readnone
|
|
declare <4 x double> @llvm.ceil.v4f64(<4 x double>) nounwind readnone
|
|
declare <8 x double> @llvm.ceil.v8f64(<8 x double>) nounwind readnone
|
|
declare <16 x double> @llvm.ceil.v16f64(<16 x double>) nounwind readnone
|
|
|
|
; FUNC-LABEL: {{^}}fceil_f64:
|
|
; CI: v_ceil_f64_e32
|
|
; SI: s_bfe_u32 [[SEXP:s[0-9]+]], {{s[0-9]+}}, 0xb0014
|
|
; SI: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000
|
|
; SI: s_add_i32 s{{[0-9]+}}, [[SEXP]], 0xfffffc01
|
|
; SI: s_lshr_b64
|
|
; SI: s_not_b64
|
|
; SI: s_and_b64
|
|
; SI-DAG: cmp_gt_i32
|
|
; SI-DAG: cndmask_b32
|
|
; SI-DAG: cndmask_b32
|
|
; SI-DAG: cmp_lt_i32
|
|
; SI-DAG: cndmask_b32
|
|
; SI-DAG: cndmask_b32
|
|
; SI-DAG: v_cmp_lt_f64
|
|
; SI-DAG: v_cmp_lg_f64
|
|
; SI: s_and_b64
|
|
; SI: v_cndmask_b32
|
|
; SI: v_cndmask_b32
|
|
; SI: v_add_f64
|
|
; SI: s_endpgm
|
|
define void @fceil_f64(double addrspace(1)* %out, double %x) {
|
|
%y = call double @llvm.ceil.f64(double %x) nounwind readnone
|
|
store double %y, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fceil_v2f64:
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
define void @fceil_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
|
|
%y = call <2 x double> @llvm.ceil.v2f64(<2 x double> %x) nounwind readnone
|
|
store <2 x double> %y, <2 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FIXME-FUNC-LABEL: {{^}}fceil_v3f64:
|
|
; FIXME-CI: v_ceil_f64_e32
|
|
; FIXME-CI: v_ceil_f64_e32
|
|
; FIXME-CI: v_ceil_f64_e32
|
|
; define void @fceil_v3f64(<3 x double> addrspace(1)* %out, <3 x double> %x) {
|
|
; %y = call <3 x double> @llvm.ceil.v3f64(<3 x double> %x) nounwind readnone
|
|
; store <3 x double> %y, <3 x double> addrspace(1)* %out
|
|
; ret void
|
|
; }
|
|
|
|
; FUNC-LABEL: {{^}}fceil_v4f64:
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
define void @fceil_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %x) {
|
|
%y = call <4 x double> @llvm.ceil.v4f64(<4 x double> %x) nounwind readnone
|
|
store <4 x double> %y, <4 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fceil_v8f64:
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
define void @fceil_v8f64(<8 x double> addrspace(1)* %out, <8 x double> %x) {
|
|
%y = call <8 x double> @llvm.ceil.v8f64(<8 x double> %x) nounwind readnone
|
|
store <8 x double> %y, <8 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fceil_v16f64:
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
; CI: v_ceil_f64_e32
|
|
define void @fceil_v16f64(<16 x double> addrspace(1)* %out, <16 x double> %x) {
|
|
%y = call <16 x double> @llvm.ceil.v16f64(<16 x double> %x) nounwind readnone
|
|
store <16 x double> %y, <16 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|