mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +01:00
cf702a78f5
This provides the low-level support to start using MVE vector types in LLVM IR, loading and storing them, passing them to __asm__ statements containing hand-written MVE vector instructions, and *if* you have the hard-float ABI turned on, using them as function parameters. (In the soft-float ABI, vector types are passed in integer registers, and combining all those 32-bit integers into a q-reg requires support for selection DAG nodes like insert_vector_elt and build_vector which aren't implemented yet for MVE. In fact I've also had to add `arm_aapcs_vfpcc` to a couple of existing tests to avoid that problem.) Specifically, this commit adds support for: * spills, reloads and register moves for MVE vector registers * ditto for the VPT predication mask that lives in VPR.P0 * make all the MVE vector types legal in ISel, and provide selection DAG patterns for BITCAST, LOAD and STORE * make loads and stores of scalar FP types conditional on `hasFPRegs()` rather than `hasVFP2Base()`. As a result a few existing tests needed their llc command lines updating to use `-mattr=-fpregs` as their method of turning off all hardware FP support. Reviewers: dmgreen, samparker, SjoerdMeijer Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D60708 llvm-svn: 364329
32 lines
1.2 KiB
LLVM
32 lines
1.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -o - %s | FileCheck %s
|
|
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -o - %s | FileCheck %s
|
|
|
|
define arm_aapcs_vfpcc <4 x i32> @vector_add_by_value(<4 x i32> %lhs, <4 x i32>%rhs) {
|
|
; CHECK-LABEL: vector_add_by_value:
|
|
; CHECK: @ %bb.0:
|
|
; CHECK-NEXT: @APP
|
|
; CHECK-NEXT: vadd.i32 q0, q0, q1
|
|
; CHECK-NEXT: @NO_APP
|
|
; CHECK-NEXT: bx lr
|
|
%result = tail call <4 x i32> asm "vadd.i32 $0,$1,$2", "=t,t,t"(<4 x i32> %lhs, <4 x i32> %rhs)
|
|
ret <4 x i32> %result
|
|
}
|
|
|
|
define void @vector_add_by_reference(<4 x i32>* %resultp, <4 x i32>* %lhsp, <4 x i32>* %rhsp) {
|
|
; CHECK-LABEL: vector_add_by_reference:
|
|
; CHECK: @ %bb.0:
|
|
; CHECK-NEXT: vldrw.u32 q0, [r1]
|
|
; CHECK-NEXT: vldrw.u32 q1, [r2]
|
|
; CHECK-NEXT: @APP
|
|
; CHECK-NEXT: vadd.i32 q0, q0, q1
|
|
; CHECK-NEXT: @NO_APP
|
|
; CHECK-NEXT: vstrw.32 q0, [r0]
|
|
; CHECK-NEXT: bx lr
|
|
%lhs = load <4 x i32>, <4 x i32>* %lhsp, align 16
|
|
%rhs = load <4 x i32>, <4 x i32>* %rhsp, align 16
|
|
%result = tail call <4 x i32> asm "vadd.i32 $0,$1,$2", "=t,t,t"(<4 x i32> %lhs, <4 x i32> %rhs)
|
|
store <4 x i32> %result, <4 x i32>* %resultp, align 16
|
|
ret void
|
|
}
|