mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
24ecb58ca9
This patch adds basic support for BFloat in the Arm backend. For now the code generation relies on fullfp16 being present. Briefly: * adds the bfloat scalar and vector types in the necessary register classes, * adjusts the calling convention to cope with bfloat argument passing and return, * adds codegen patterns for moves, loads and stores. It's tested mostly by the intrinsic patches that depend on it (load/store, convert/copy). The following people contributed to this patch: * Alexandros Lamprineas * Ties Stuij Differential Revision: https://reviews.llvm.org/D81373
107 lines
2.8 KiB
LLVM
107 lines
2.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -float-abi hard -mattr=+bf16,+fullfp16 < %s | FileCheck %s --check-prefix=HARD
|
|
; RUN: llc -float-abi soft -mattr=+bf16,+fullfp16 < %s | FileCheck %s --check-prefix=SOFT
|
|
|
|
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
|
|
target triple = "armv8.6a-arm-none-eabi"
|
|
|
|
define bfloat @load_scalar_bf(bfloat* %addr) {
|
|
; HARD-LABEL: load_scalar_bf:
|
|
; HARD: @ %bb.0: @ %entry
|
|
; HARD-NEXT: vldr.16 s0, [r0]
|
|
; HARD-NEXT: bx lr
|
|
;
|
|
; SOFT-LABEL: load_scalar_bf:
|
|
; SOFT: @ %bb.0: @ %entry
|
|
; SOFT-NEXT: vldr.16 s0, [r0]
|
|
; SOFT-NEXT: vmov r0, s0
|
|
; SOFT-NEXT: bx lr
|
|
entry:
|
|
%0 = load bfloat, bfloat* %addr, align 2
|
|
ret bfloat %0
|
|
}
|
|
|
|
define void @store_scalar_bf(bfloat %v, bfloat* %addr) {
|
|
; HARD-LABEL: store_scalar_bf:
|
|
; HARD: @ %bb.0: @ %entry
|
|
; HARD-NEXT: vstr.16 s0, [r0]
|
|
; HARD-NEXT: bx lr
|
|
;
|
|
; SOFT-LABEL: store_scalar_bf:
|
|
; SOFT: @ %bb.0: @ %entry
|
|
; SOFT-NEXT: vmov.f16 s0, r0
|
|
; SOFT-NEXT: vstr.16 s0, [r1]
|
|
; SOFT-NEXT: bx lr
|
|
entry:
|
|
store bfloat %v, bfloat* %addr, align 2
|
|
ret void
|
|
}
|
|
|
|
define <4 x bfloat> @load_vector4_bf(<4 x bfloat>* %addr) {
|
|
; HARD-LABEL: load_vector4_bf:
|
|
; HARD: @ %bb.0: @ %entry
|
|
; HARD-NEXT: vldr d0, [r0]
|
|
; HARD-NEXT: bx lr
|
|
;
|
|
; SOFT-LABEL: load_vector4_bf:
|
|
; SOFT: @ %bb.0: @ %entry
|
|
; SOFT-NEXT: vldr d16, [r0]
|
|
; SOFT-NEXT: vmov r0, r1, d16
|
|
; SOFT-NEXT: bx lr
|
|
entry:
|
|
%0 = load <4 x bfloat>, <4 x bfloat>* %addr, align 8
|
|
ret <4 x bfloat> %0
|
|
}
|
|
|
|
define void @store_vector4_bf(<4 x bfloat> %v, <4 x bfloat>* %addr) {
|
|
; HARD-LABEL: store_vector4_bf:
|
|
; HARD: @ %bb.0: @ %entry
|
|
; HARD-NEXT: vstr d0, [r0]
|
|
; HARD-NEXT: bx lr
|
|
;
|
|
; SOFT-LABEL: store_vector4_bf:
|
|
; SOFT: @ %bb.0: @ %entry
|
|
; SOFT-NEXT: strd r0, r1, [r2]
|
|
; SOFT-NEXT: bx lr
|
|
entry:
|
|
store <4 x bfloat> %v, <4 x bfloat>* %addr, align 8
|
|
ret void
|
|
}
|
|
|
|
define <8 x bfloat> @load_vector8_bf(<8 x bfloat>* %addr) {
|
|
; HARD-LABEL: load_vector8_bf:
|
|
; HARD: @ %bb.0: @ %entry
|
|
; HARD-NEXT: vld1.64 {d0, d1}, [r0]
|
|
; HARD-NEXT: bx lr
|
|
;
|
|
; SOFT-LABEL: load_vector8_bf:
|
|
; SOFT: @ %bb.0: @ %entry
|
|
; SOFT-NEXT: vld1.64 {d16, d17}, [r0]
|
|
; SOFT-NEXT: vmov r0, r1, d16
|
|
; SOFT-NEXT: vmov r2, r3, d17
|
|
; SOFT-NEXT: bx lr
|
|
entry:
|
|
%0 = load <8 x bfloat>, <8 x bfloat>* %addr, align 8
|
|
ret <8 x bfloat> %0
|
|
}
|
|
|
|
define void @store_vector8_bf(<8 x bfloat> %v, <8 x bfloat>* %addr) {
|
|
; HARD-LABEL: store_vector8_bf:
|
|
; HARD: @ %bb.0: @ %entry
|
|
; HARD-NEXT: vst1.64 {d0, d1}, [r0]
|
|
; HARD-NEXT: bx lr
|
|
;
|
|
; SOFT-LABEL: store_vector8_bf:
|
|
; SOFT: @ %bb.0: @ %entry
|
|
; SOFT-NEXT: vmov d17, r2, r3
|
|
; SOFT-NEXT: ldr r12, [sp]
|
|
; SOFT-NEXT: vmov d16, r0, r1
|
|
; SOFT-NEXT: vst1.64 {d16, d17}, [r12]
|
|
; SOFT-NEXT: bx lr
|
|
entry:
|
|
store <8 x bfloat> %v, <8 x bfloat>* %addr, align 8
|
|
ret void
|
|
}
|
|
|
|
|