1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00
llvm-mirror/test/CodeGen/ARM/arm-matmul.ll
Luke Geeson 09ef958be1 [AArch32] Armv8.6-a Matrix Mult Assembly + Intrinsics
This patch upstreams support for the Armv8.6-a Matrix Multiplication
Extension. A summary of the features can be found here:

https://community.arm.com/developer/ip-products/processors/b/processors-ip-blog/posts/arm-architecture-developments-armv8-6-a

This patch includes:

- Assembly support for AArch32
- Intrinsics Support for AArch32 Neon Intrinsics for Matrix
  Multiplication

Note: these extensions are optional in the 8.6a architecture and so have
to be enabled by default

No additional IR types or C Types are needed for this extension.

This is part of a patch series, starting with BFloat16 support and
the other components in the armv8.6a extension (in previous patches
linked in phabricator)

Based on work by:
- Luke Geeson
- Oliver Stannard
- Luke Cheeseman

Reviewers: t.p.northover, miyuki

Reviewed By: miyuki

Subscribers: miyuki, ostannard, kristof.beyls, hiraditya, danielkiss,
cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D77872
2020-04-24 15:54:06 +01:00

84 lines
3.6 KiB
LLVM

; RUN: llc -mtriple=arm-none-linux-gnu -mattr=+neon,+i8mm -float-abi=hard < %s -o -| FileCheck %s
define <4 x i32> @smmla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) {
entry:
; CHECK-LABEL: smmla.v4i32.v16i8
; CHECK: vsmmla.s8 q0, q1, q2
%vmmla1.i = tail call <4 x i32> @llvm.arm.neon.smmla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) #3
ret <4 x i32> %vmmla1.i
}
define <4 x i32> @ummla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) {
entry:
; CHECK-LABEL: ummla.v4i32.v16i8
; CHECK: vummla.u8 q0, q1, q2
%vmmla1.i = tail call <4 x i32> @llvm.arm.neon.ummla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) #3
ret <4 x i32> %vmmla1.i
}
define <4 x i32> @usmmla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) {
entry:
; CHECK-LABEL: usmmla.v4i32.v16i8
; CHECK: vusmmla.s8 q0, q1, q2
%vusmmla1.i = tail call <4 x i32> @llvm.arm.neon.usmmla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) #3
ret <4 x i32> %vusmmla1.i
}
define <2 x i32> @usdot.v2i32.v8i8(<2 x i32> %r, <8 x i8> %a, <8 x i8> %b) {
entry:
; CHECK-LABEL: usdot.v2i32.v8i8
; CHECK: vusdot.s8 d0, d1, d2
%vusdot1.i = tail call <2 x i32> @llvm.arm.neon.usdot.v2i32.v8i8(<2 x i32> %r, <8 x i8> %a, <8 x i8> %b) #3
ret <2 x i32> %vusdot1.i
}
define <2 x i32> @usdot_lane.v2i32.v8i8(<2 x i32> %r, <8 x i8> %a, <8 x i8> %b) {
entry:
; CHECK-LABEL: usdot_lane.v2i32.v8i8
; CHECK: vusdot.s8 d0, d1, d2[0]
%0 = bitcast <8 x i8> %b to <2 x i32>
%shuffle = shufflevector <2 x i32> %0, <2 x i32> undef, <2 x i32> zeroinitializer
%1 = bitcast <2 x i32> %shuffle to <8 x i8>
%vusdot1.i = tail call <2 x i32> @llvm.arm.neon.usdot.v2i32.v8i8(<2 x i32> %r, <8 x i8> %a, <8 x i8> %1) #3
ret <2 x i32> %vusdot1.i
}
define <2 x i32> @sudot_lane.v2i32.v8i8(<2 x i32> %r, <8 x i8> %a, <8 x i8> %b) {
entry:
; CHECK-LABEL: sudot_lane.v2i32.v8i8
; CHECK: vsudot.u8 d0, d1, d2[0]
%0 = bitcast <8 x i8> %b to <2 x i32>
%shuffle = shufflevector <2 x i32> %0, <2 x i32> undef, <2 x i32> zeroinitializer
%1 = bitcast <2 x i32> %shuffle to <8 x i8>
%vusdot1.i = tail call <2 x i32> @llvm.arm.neon.usdot.v2i32.v8i8(<2 x i32> %r, <8 x i8> %1, <8 x i8> %a) #3
ret <2 x i32> %vusdot1.i
}
define <4 x i32> @usdotq_lane.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <8 x i8> %b) {
entry:
; CHECK-LABEL: usdotq_lane.v4i32.v16i8
; CHECK: vusdot.s8 q0, q1, d4[0]
%0 = bitcast <8 x i8> %b to <2 x i32>
%shuffle = shufflevector <2 x i32> %0, <2 x i32> undef, <4 x i32> zeroinitializer
%1 = bitcast <4 x i32> %shuffle to <16 x i8>
%vusdot1.i = tail call <4 x i32> @llvm.arm.neon.usdot.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %1) #3
ret <4 x i32> %vusdot1.i
}
define <4 x i32> @sudotq_lane.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <8 x i8> %b) {
entry:
; CHECK-LABEL: sudotq_lane.v4i32.v16i8
; CHECK: vsudot.u8 q0, q1, d4[0]
%0 = bitcast <8 x i8> %b to <2 x i32>
%shuffle = shufflevector <2 x i32> %0, <2 x i32> undef, <4 x i32> zeroinitializer
%1 = bitcast <4 x i32> %shuffle to <16 x i8>
%vusdot1.i = tail call <4 x i32> @llvm.arm.neon.usdot.v4i32.v16i8(<4 x i32> %r, <16 x i8> %1, <16 x i8> %a) #3
ret <4 x i32> %vusdot1.i
}
declare <4 x i32> @llvm.arm.neon.smmla.v4i32.v16i8(<4 x i32>, <16 x i8>, <16 x i8>) #2
declare <4 x i32> @llvm.arm.neon.ummla.v4i32.v16i8(<4 x i32>, <16 x i8>, <16 x i8>) #2
declare <4 x i32> @llvm.arm.neon.usmmla.v4i32.v16i8(<4 x i32>, <16 x i8>, <16 x i8>) #2
declare <2 x i32> @llvm.arm.neon.usdot.v2i32.v8i8(<2 x i32>, <8 x i8>, <8 x i8>) #2
declare <4 x i32> @llvm.arm.neon.usdot.v4i32.v16i8(<4 x i32>, <16 x i8>, <16 x i8>) #2