mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 13:02:52 +02:00
5f490e6f09
This re-applies r223862, r224198, r224203, and r224754, which were reverted in r228129 because they exposed Clang misalignment problems when self-hosting. The combine caused the crashes because we turned ISD::LOAD/STORE nodes to ARMISD::VLD1/VST1_UPD nodes. When selecting addressing modes, we were very lax for the former, and only emitted the alignment operand (as in "[r1:128]") when it was larger than the standard alignment of the memory type. However, for ARMISD nodes, we just used the MMO alignment, no matter what. In our case, we turned ISD nodes to ARMISD nodes, and this caused the alignment operands to start being emitted. And that's how we exposed alignment problems that were ignored before (but I believe would have been caught with SCTRL.A==1?). To fix this, we can just mirror the hack done for ISD nodes: only take into account the MMO alignment when the access is overaligned. Original commit message: We used to only combine intrinsics, and turn them into VLD1_UPD/VST1_UPD when the base pointer is incremented after the load/store. We can do the same thing for generic load/stores. Note that we can only combine the first load/store+adds pair in a sequence (as might be generated for a v16f32 load for instance), because other combines turn the base pointer addition chain (each computing the address of the next load, from the address of the last load) into independent additions (common base pointer + this load's offset). rdar://19717869, rdar://14062261. llvm-svn: 229932
259 lines
8.1 KiB
LLVM
259 lines
8.1 KiB
LLVM
; RUN: llc < %s | FileCheck %s
|
|
|
|
target datalayout = "e-m:o-p:32:32-i1:8:32-i8:8:32-i16:16:32-f64:32:64-v64:32:64-v128:32:128-a:0:32-n32-S32"
|
|
target triple = "thumbv7s-apple-ios8.0.0"
|
|
|
|
define void @store_v8i8(<8 x i8>** %ptr, <8 x i8> %val) {
|
|
;CHECK-LABEL: store_v8i8:
|
|
;CHECK: str r1, [r0]
|
|
%A = load <8 x i8>** %ptr
|
|
store <8 x i8> %val, <8 x i8>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v8i8_update(<8 x i8>** %ptr, <8 x i8> %val) {
|
|
;CHECK-LABEL: store_v8i8_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <8 x i8>** %ptr
|
|
store <8 x i8> %val, <8 x i8>* %A, align 1
|
|
%inc = getelementptr <8 x i8>* %A, i38 1
|
|
store <8 x i8>* %inc, <8 x i8>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v4i16(<4 x i16>** %ptr, <4 x i16> %val) {
|
|
;CHECK-LABEL: store_v4i16:
|
|
;CHECK: str r1, [r0]
|
|
%A = load <4 x i16>** %ptr
|
|
store <4 x i16> %val, <4 x i16>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v4i16_update(<4 x i16>** %ptr, <4 x i16> %val) {
|
|
;CHECK-LABEL: store_v4i16_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <4 x i16>** %ptr
|
|
store <4 x i16> %val, <4 x i16>* %A, align 1
|
|
%inc = getelementptr <4 x i16>* %A, i34 1
|
|
store <4 x i16>* %inc, <4 x i16>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2i32(<2 x i32>** %ptr, <2 x i32> %val) {
|
|
;CHECK-LABEL: store_v2i32:
|
|
;CHECK: str r1, [r0]
|
|
%A = load <2 x i32>** %ptr
|
|
store <2 x i32> %val, <2 x i32>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2i32_update(<2 x i32>** %ptr, <2 x i32> %val) {
|
|
;CHECK-LABEL: store_v2i32_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <2 x i32>** %ptr
|
|
store <2 x i32> %val, <2 x i32>* %A, align 1
|
|
%inc = getelementptr <2 x i32>* %A, i32 1
|
|
store <2 x i32>* %inc, <2 x i32>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2f32(<2 x float>** %ptr, <2 x float> %val) {
|
|
;CHECK-LABEL: store_v2f32:
|
|
;CHECK: str r1, [r0]
|
|
%A = load <2 x float>** %ptr
|
|
store <2 x float> %val, <2 x float>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2f32_update(<2 x float>** %ptr, <2 x float> %val) {
|
|
;CHECK-LABEL: store_v2f32_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <2 x float>** %ptr
|
|
store <2 x float> %val, <2 x float>* %A, align 1
|
|
%inc = getelementptr <2 x float>* %A, i32 1
|
|
store <2 x float>* %inc, <2 x float>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v1i64(<1 x i64>** %ptr, <1 x i64> %val) {
|
|
;CHECK-LABEL: store_v1i64:
|
|
;CHECK: str r1, [r0]
|
|
%A = load <1 x i64>** %ptr
|
|
store <1 x i64> %val, <1 x i64>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v1i64_update(<1 x i64>** %ptr, <1 x i64> %val) {
|
|
;CHECK-LABEL: store_v1i64_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <1 x i64>** %ptr
|
|
store <1 x i64> %val, <1 x i64>* %A, align 1
|
|
%inc = getelementptr <1 x i64>* %A, i31 1
|
|
store <1 x i64>* %inc, <1 x i64>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v16i8(<16 x i8>** %ptr, <16 x i8> %val) {
|
|
;CHECK-LABEL: store_v16i8:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
|
|
%A = load <16 x i8>** %ptr
|
|
store <16 x i8> %val, <16 x i8>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v16i8_update(<16 x i8>** %ptr, <16 x i8> %val) {
|
|
;CHECK-LABEL: store_v16i8_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <16 x i8>** %ptr
|
|
store <16 x i8> %val, <16 x i8>* %A, align 1
|
|
%inc = getelementptr <16 x i8>* %A, i316 1
|
|
store <16 x i8>* %inc, <16 x i8>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v8i16(<8 x i16>** %ptr, <8 x i16> %val) {
|
|
;CHECK-LABEL: store_v8i16:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
|
|
%A = load <8 x i16>** %ptr
|
|
store <8 x i16> %val, <8 x i16>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v8i16_update(<8 x i16>** %ptr, <8 x i16> %val) {
|
|
;CHECK-LABEL: store_v8i16_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <8 x i16>** %ptr
|
|
store <8 x i16> %val, <8 x i16>* %A, align 1
|
|
%inc = getelementptr <8 x i16>* %A, i38 1
|
|
store <8 x i16>* %inc, <8 x i16>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v4i32(<4 x i32>** %ptr, <4 x i32> %val) {
|
|
;CHECK-LABEL: store_v4i32:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
|
|
%A = load <4 x i32>** %ptr
|
|
store <4 x i32> %val, <4 x i32>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v4i32_update(<4 x i32>** %ptr, <4 x i32> %val) {
|
|
;CHECK-LABEL: store_v4i32_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <4 x i32>** %ptr
|
|
store <4 x i32> %val, <4 x i32>* %A, align 1
|
|
%inc = getelementptr <4 x i32>* %A, i34 1
|
|
store <4 x i32>* %inc, <4 x i32>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v4f32(<4 x float>** %ptr, <4 x float> %val) {
|
|
;CHECK-LABEL: store_v4f32:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
|
|
%A = load <4 x float>** %ptr
|
|
store <4 x float> %val, <4 x float>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v4f32_update(<4 x float>** %ptr, <4 x float> %val) {
|
|
;CHECK-LABEL: store_v4f32_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <4 x float>** %ptr
|
|
store <4 x float> %val, <4 x float>* %A, align 1
|
|
%inc = getelementptr <4 x float>* %A, i34 1
|
|
store <4 x float>* %inc, <4 x float>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2i64(<2 x i64>** %ptr, <2 x i64> %val) {
|
|
;CHECK-LABEL: store_v2i64:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
|
|
%A = load <2 x i64>** %ptr
|
|
store <2 x i64> %val, <2 x i64>* %A, align 1
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2i64_update(<2 x i64>** %ptr, <2 x i64> %val) {
|
|
;CHECK-LABEL: store_v2i64_update:
|
|
;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <2 x i64>** %ptr
|
|
store <2 x i64> %val, <2 x i64>* %A, align 1
|
|
%inc = getelementptr <2 x i64>* %A, i32 1
|
|
store <2 x i64>* %inc, <2 x i64>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2i64_update_aligned2(<2 x i64>** %ptr, <2 x i64> %val) {
|
|
;CHECK-LABEL: store_v2i64_update_aligned2:
|
|
;CHECK: vst1.16 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <2 x i64>** %ptr
|
|
store <2 x i64> %val, <2 x i64>* %A, align 2
|
|
%inc = getelementptr <2 x i64>* %A, i32 1
|
|
store <2 x i64>* %inc, <2 x i64>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2i64_update_aligned4(<2 x i64>** %ptr, <2 x i64> %val) {
|
|
;CHECK-LABEL: store_v2i64_update_aligned4:
|
|
;CHECK: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <2 x i64>** %ptr
|
|
store <2 x i64> %val, <2 x i64>* %A, align 4
|
|
%inc = getelementptr <2 x i64>* %A, i32 1
|
|
store <2 x i64>* %inc, <2 x i64>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2i64_update_aligned8(<2 x i64>** %ptr, <2 x i64> %val) {
|
|
;CHECK-LABEL: store_v2i64_update_aligned8:
|
|
;CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
|
|
%A = load <2 x i64>** %ptr
|
|
store <2 x i64> %val, <2 x i64>* %A, align 8
|
|
%inc = getelementptr <2 x i64>* %A, i32 1
|
|
store <2 x i64>* %inc, <2 x i64>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @store_v2i64_update_aligned16(<2 x i64>** %ptr, <2 x i64> %val) {
|
|
;CHECK-LABEL: store_v2i64_update_aligned16:
|
|
;CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}:128]!
|
|
%A = load <2 x i64>** %ptr
|
|
store <2 x i64> %val, <2 x i64>* %A, align 16
|
|
%inc = getelementptr <2 x i64>* %A, i32 1
|
|
store <2 x i64>* %inc, <2 x i64>** %ptr
|
|
ret void
|
|
}
|
|
|
|
define void @truncstore_v4i32tov4i8(<4 x i8>** %ptr, <4 x i32> %val) {
|
|
;CHECK-LABEL: truncstore_v4i32tov4i8:
|
|
;CHECK: ldr.w r9, [sp]
|
|
;CHECK: vmov {{d[0-9]+}}, r3, r9
|
|
;CHECK: vmov {{d[0-9]+}}, r1, r2
|
|
;CHECK: vmovn.i32 [[VECLO:d[0-9]+]], {{q[0-9]+}}
|
|
;CHECK: vuzp.8 [[VECLO]], {{d[0-9]+}}
|
|
;CHECK: ldr r[[PTRREG:[0-9]+]], [r0]
|
|
;CHECK: vst1.32 {[[VECLO]][0]}, [r[[PTRREG]]:32]
|
|
%A = load <4 x i8>** %ptr
|
|
%trunc = trunc <4 x i32> %val to <4 x i8>
|
|
store <4 x i8> %trunc, <4 x i8>* %A, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @truncstore_v4i32tov4i8_fake_update(<4 x i8>** %ptr, <4 x i32> %val) {
|
|
;CHECK-LABEL: truncstore_v4i32tov4i8_fake_update:
|
|
;CHECK: ldr.w r9, [sp]
|
|
;CHECK: vmov {{d[0-9]+}}, r3, r9
|
|
;CHECK: vmov {{d[0-9]+}}, r1, r2
|
|
;CHECK: movs [[IMM16:r[0-9]+]], #16
|
|
;CHECK: vmovn.i32 [[VECLO:d[0-9]+]], {{q[0-9]+}}
|
|
;CHECK: vuzp.8 [[VECLO]], {{d[0-9]+}}
|
|
;CHECK: ldr r[[PTRREG:[0-9]+]], [r0]
|
|
;CHECK: vst1.32 {[[VECLO]][0]}, [r[[PTRREG]]:32], [[IMM16]]
|
|
;CHECK: str r[[PTRREG]], [r0]
|
|
%A = load <4 x i8>** %ptr
|
|
%trunc = trunc <4 x i32> %val to <4 x i8>
|
|
store <4 x i8> %trunc, <4 x i8>* %A, align 4
|
|
%inc = getelementptr <4 x i8>* %A, i38 4
|
|
store <4 x i8>* %inc, <4 x i8>** %ptr
|
|
ret void
|
|
}
|