mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 04:52:54 +02:00
2b32675441
Armv6 introduced instructions to perform 32-bit SIMD operations. The purpose of this pass is to do some straightforward IR pattern matching to create ACLE DSP intrinsics, which map on these 32-bit SIMD operations. Currently, only the SMLAD instruction gets recognised. This instruction performs two multiplications with 16-bit operands, and stores the result in an accumulator. We will follow this up with patches to recognise SMLAD in more cases, and also to generate other DSP instructions (like e.g. SADD16). Patch by: Sam Parker and Sjoerd Meijer Differential Revision: https://reviews.llvm.org/D48128 llvm-svn: 335850
51 lines
1.8 KiB
LLVM
51 lines
1.8 KiB
LLVM
; RUN: opt -mtriple=arm-arm-eabi -mcpu=cortex-m33 < %s -parallel-dsp -S | FileCheck %s
|
|
;
|
|
; Alias check: check that the rewrite isn't triggered when there's a store
|
|
; instruction possibly aliasing any mul load operands; arguments are passed
|
|
; without 'restrict' enabled.
|
|
;
|
|
; CHECK-NOT: call i32 @llvm.arm.smlad
|
|
;
|
|
define dso_local i32 @test(i32 %arg, i32* nocapture %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
|
|
entry:
|
|
%cmp24 = icmp sgt i32 %arg, 0
|
|
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
|
|
|
|
for.body.preheader:
|
|
%.pre = load i16, i16* %arg3, align 2
|
|
%.pre27 = load i16, i16* %arg2, align 2
|
|
br label %for.body
|
|
|
|
for.cond.cleanup:
|
|
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
|
|
ret i32 %mac1.0.lcssa
|
|
|
|
for.body:
|
|
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
|
|
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
|
|
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
|
|
%0 = load i16, i16* %arrayidx, align 2
|
|
|
|
; Store inserted here, aliasing with arrayidx, arrayidx1, arrayidx3
|
|
store i16 42, i16* %arrayidx, align 2
|
|
|
|
%add = add nuw nsw i32 %i.025, 1
|
|
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
|
|
%1 = load i16, i16* %arrayidx1, align 2
|
|
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
|
|
%2 = load i16, i16* %arrayidx3, align 2
|
|
%conv = sext i16 %2 to i32
|
|
%conv4 = sext i16 %0 to i32
|
|
%mul = mul nsw i32 %conv, %conv4
|
|
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
|
|
%3 = load i16, i16* %arrayidx6, align 2
|
|
%conv7 = sext i16 %3 to i32
|
|
%conv8 = sext i16 %1 to i32
|
|
%mul9 = mul nsw i32 %conv7, %conv8
|
|
%add10 = add i32 %mul, %mac1.026
|
|
%add11 = add i32 %mul9, %add10
|
|
%exitcond = icmp ne i32 %add, %arg
|
|
br i1 %exitcond, label %for.body, label %for.cond.cleanup
|
|
}
|
|
|