[llvm] [LoongArch] Add patterns to support `[x]vadda.{b/h/w/d}` generation (PR #160674)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Sep 25 02:36:24 PDT 2025
https://github.com/zhaoqi5 created https://github.com/llvm/llvm-project/pull/160674
This commit add patterns for lsx and lasx to support generating `[x]vadda.{b/h/w/d}` instructions.
Note: For convenience, this commit also set `ISD::ABS` as legal. As shown in the tests, this brings no change to the results, just same as the results obtained from expanding it before. But, setting it as legal brings more vectorization opportunities to IR transformation which may bring more vector optimization chances for later stages and the backend.
>From 6537eae0f0948cad69196364b252f2a61c4ff250 Mon Sep 17 00:00:00 2001
From: Qi Zhao <zhaoqi01 at loongson.cn>
Date: Thu, 25 Sep 2025 17:09:23 +0800
Subject: [PATCH] [LoongArch] Add patterns to support `[x]vadda.{b/h/w/d}`
generation
This commit add patterns for lsx and lasx to support generating
`[x]vadda.{b/h/w/d}` instructions.
Note: For convenience, this commit also set `ISD::ABS` as legal.
As shown in the tests, this brings no change to the results,
just same as the results obtained from expanding it before.
But, setting it as legal brings more vectorization opportunities
to IR transformation which may bring more vector optimization
chances for later stages and the backend.
---
.../LoongArch/LoongArchISelLowering.cpp | 2 +
.../LoongArch/LoongArchLASXInstrInfo.td | 16 +++
.../Target/LoongArch/LoongArchLSXInstrInfo.td | 16 +++
llvm/test/CodeGen/LoongArch/lasx/abs.ll | 128 ++++++++++++++++++
.../LoongArch/lasx/ir-instruction/adda.ll | 24 +---
llvm/test/CodeGen/LoongArch/lsx/abs.ll | 128 ++++++++++++++++++
.../LoongArch/lsx/ir-instruction/adda.ll | 24 +---
7 files changed, 298 insertions(+), 40 deletions(-)
create mode 100644 llvm/test/CodeGen/LoongArch/lasx/abs.ll
create mode 100644 llvm/test/CodeGen/LoongArch/lsx/abs.ll
diff --git a/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp b/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
index 32baa2d111270..3037234ebf4f5 100644
--- a/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
+++ b/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
@@ -340,6 +340,7 @@ LoongArchTargetLowering::LoongArchTargetLowering(const TargetMachine &TM,
{ISD::SETNE, ISD::SETGE, ISD::SETGT, ISD::SETUGE, ISD::SETUGT}, VT,
Expand);
setOperationAction(ISD::SCALAR_TO_VECTOR, VT, Custom);
+ setOperationAction(ISD::ABS, VT, Legal);
setOperationAction(ISD::ABDS, VT, Legal);
setOperationAction(ISD::ABDU, VT, Legal);
setOperationAction(ISD::SADDSAT, VT, Legal);
@@ -419,6 +420,7 @@ LoongArchTargetLowering::LoongArchTargetLowering(const TargetMachine &TM,
{ISD::SETNE, ISD::SETGE, ISD::SETGT, ISD::SETUGE, ISD::SETUGT}, VT,
Expand);
setOperationAction(ISD::SCALAR_TO_VECTOR, VT, Custom);
+ setOperationAction(ISD::ABS, VT, Legal);
setOperationAction(ISD::ABDS, VT, Legal);
setOperationAction(ISD::ABDU, VT, Legal);
setOperationAction(ISD::SADDSAT, VT, Legal);
diff --git a/llvm/lib/Target/LoongArch/LoongArchLASXInstrInfo.td b/llvm/lib/Target/LoongArch/LoongArchLASXInstrInfo.td
index adfe990ba1234..bbc0489620193 100644
--- a/llvm/lib/Target/LoongArch/LoongArchLASXInstrInfo.td
+++ b/llvm/lib/Target/LoongArch/LoongArchLASXInstrInfo.td
@@ -2015,10 +2015,26 @@ def : Pat<(v4i32(fp_to_uint v4f64:$vj)),
(XVFTINTRZ_LU_D v4f64:$vj)),
sub_128)>;
+// abs
+def : Pat<(abs v32i8:$xj), (XVMAX_B v32i8:$xj, (XVNEG_B v32i8:$xj))>;
+def : Pat<(abs v16i16:$xj), (XVMAX_H v16i16:$xj, (XVNEG_H v16i16:$xj))>;
+def : Pat<(abs v8i32:$xj), (XVMAX_W v8i32:$xj, (XVNEG_W v8i32:$xj))>;
+def : Pat<(abs v4i64:$xj), (XVMAX_D v4i64:$xj, (XVNEG_D v4i64:$xj))>;
+
// XVABSD_{B/H/W/D}[U]
defm : PatXrXr<abds, "XVABSD">;
defm : PatXrXrU<abdu, "XVABSD">;
+// XVADDA_{B/H/W/D}
+def : Pat<(add (v32i8 (abs v32i8:$xj)), (v32i8 (abs v32i8:$xk))),
+ (XVADDA_B v32i8:$xj, v32i8:$xk)>;
+def : Pat<(add (v16i16 (abs v16i16:$xj)), (v16i16 (abs v16i16:$xk))),
+ (XVADDA_H v16i16:$xj, v16i16:$xk)>;
+def : Pat<(add (v8i32 (abs v8i32:$xj)), (v8i32 (abs v8i32:$xk))),
+ (XVADDA_W v8i32:$xj, v8i32:$xk)>;
+def : Pat<(add (v4i64 (abs v4i64:$xj)), (v4i64 (abs v4i64:$xk))),
+ (XVADDA_D v4i64:$xj, v4i64:$xk)>;
+
// XVSADD_{B/H/W/D}[U], XVSSUB_{B/H/W/D}[U]
defm : PatXrXr<saddsat, "XVSADD">;
defm : PatXrXr<ssubsat, "XVSSUB">;
diff --git a/llvm/lib/Target/LoongArch/LoongArchLSXInstrInfo.td b/llvm/lib/Target/LoongArch/LoongArchLSXInstrInfo.td
index d99a57e562528..72029710c57fc 100644
--- a/llvm/lib/Target/LoongArch/LoongArchLSXInstrInfo.td
+++ b/llvm/lib/Target/LoongArch/LoongArchLSXInstrInfo.td
@@ -2153,10 +2153,26 @@ def : Pat<(f32 f32imm_vldi:$in),
def : Pat<(f64 f64imm_vldi:$in),
(f64 (EXTRACT_SUBREG (VLDI (to_f64imm_vldi f64imm_vldi:$in)), sub_64))>;
+// abs
+def : Pat<(abs v16i8:$vj), (VMAX_B v16i8:$vj, (VNEG_B v16i8:$vj))>;
+def : Pat<(abs v8i16:$vj), (VMAX_H v8i16:$vj, (VNEG_H v8i16:$vj))>;
+def : Pat<(abs v4i32:$vj), (VMAX_W v4i32:$vj, (VNEG_W v4i32:$vj))>;
+def : Pat<(abs v2i64:$vj), (VMAX_D v2i64:$vj, (VNEG_D v2i64:$vj))>;
+
// VABSD_{B/H/W/D}[U]
defm : PatVrVr<abds, "VABSD">;
defm : PatVrVrU<abdu, "VABSD">;
+// VADDA_{B/H/W/D}
+def : Pat<(add (v16i8 (abs v16i8:$vj)), (v16i8 (abs v16i8:$vk))),
+ (VADDA_B v16i8:$vj, v16i8:$vk)>;
+def : Pat<(add (v8i16 (abs v8i16:$vj)), (v8i16 (abs v8i16:$vk))),
+ (VADDA_H v8i16:$vj, v8i16:$vk)>;
+def : Pat<(add (v4i32 (abs v4i32:$vj)), (v4i32 (abs v4i32:$vk))),
+ (VADDA_W v4i32:$vj, v4i32:$vk)>;
+def : Pat<(add (v2i64 (abs v2i64:$vj)), (v2i64 (abs v2i64:$vk))),
+ (VADDA_D v2i64:$vj, v2i64:$vk)>;
+
// VSADD_{B/H/W/D}[U], VSSUB_{B/H/W/D}[U]
defm : PatVrVr<saddsat, "VSADD">;
defm : PatVrVr<ssubsat, "VSSUB">;
diff --git a/llvm/test/CodeGen/LoongArch/lasx/abs.ll b/llvm/test/CodeGen/LoongArch/lasx/abs.ll
new file mode 100644
index 0000000000000..e3b0d04d92d75
--- /dev/null
+++ b/llvm/test/CodeGen/LoongArch/lasx/abs.ll
@@ -0,0 +1,128 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lasx < %s | FileCheck %s
+; RUN: llc --mtriple=loongarch64 --mattr=+lasx < %s | FileCheck %s
+
+define void @vabs_b(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_b:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: xvld $xr0, $a1, 0
+; CHECK-NEXT: xvneg.b $xr1, $xr0
+; CHECK-NEXT: xvmax.b $xr0, $xr0, $xr1
+; CHECK-NEXT: xvst $xr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <32 x i8>, ptr %src
+ %b = tail call <32 x i8> @llvm.abs.v32i8(<32 x i8> %a, i1 true)
+ store <32 x i8> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_b_1(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_b_1:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: xvld $xr0, $a1, 0
+; CHECK-NEXT: xvneg.b $xr1, $xr0
+; CHECK-NEXT: xvmax.b $xr0, $xr0, $xr1
+; CHECK-NEXT: xvst $xr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <32 x i8>, ptr %src
+ %b = tail call <32 x i8> @llvm.abs.v32i8(<32 x i8> %a, i1 false)
+ store <32 x i8> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_h(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_h:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: xvld $xr0, $a1, 0
+; CHECK-NEXT: xvneg.h $xr1, $xr0
+; CHECK-NEXT: xvmax.h $xr0, $xr0, $xr1
+; CHECK-NEXT: xvst $xr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <16 x i16>, ptr %src
+ %b = tail call <16 x i16> @llvm.abs.v16i16(<16 x i16> %a, i1 true)
+ store <16 x i16> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_h_1(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_h_1:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: xvld $xr0, $a1, 0
+; CHECK-NEXT: xvneg.h $xr1, $xr0
+; CHECK-NEXT: xvmax.h $xr0, $xr0, $xr1
+; CHECK-NEXT: xvst $xr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <16 x i16>, ptr %src
+ %b = tail call <16 x i16> @llvm.abs.v16i16(<16 x i16> %a, i1 false)
+ store <16 x i16> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_w(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_w:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: xvld $xr0, $a1, 0
+; CHECK-NEXT: xvneg.w $xr1, $xr0
+; CHECK-NEXT: xvmax.w $xr0, $xr0, $xr1
+; CHECK-NEXT: xvst $xr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <8 x i32>, ptr %src
+ %b = tail call <8 x i32> @llvm.abs.v8i32(<8 x i32> %a, i1 true)
+ store <8 x i32> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_w_1(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_w_1:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: xvld $xr0, $a1, 0
+; CHECK-NEXT: xvneg.w $xr1, $xr0
+; CHECK-NEXT: xvmax.w $xr0, $xr0, $xr1
+; CHECK-NEXT: xvst $xr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <8 x i32>, ptr %src
+ %b = tail call <8 x i32> @llvm.abs.v8i32(<8 x i32> %a, i1 false)
+ store <8 x i32> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_d(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_d:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: xvld $xr0, $a1, 0
+; CHECK-NEXT: xvneg.d $xr1, $xr0
+; CHECK-NEXT: xvmax.d $xr0, $xr0, $xr1
+; CHECK-NEXT: xvst $xr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <4 x i64>, ptr %src
+ %b = tail call <4 x i64> @llvm.abs.v4i64(<4 x i64> %a, i1 true)
+ store <4 x i64> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_d_1(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_d_1:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: xvld $xr0, $a1, 0
+; CHECK-NEXT: xvneg.d $xr1, $xr0
+; CHECK-NEXT: xvmax.d $xr0, $xr0, $xr1
+; CHECK-NEXT: xvst $xr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <4 x i64>, ptr %src
+ %b = tail call <4 x i64> @llvm.abs.v4i64(<4 x i64> %a, i1 false)
+ store <4 x i64> %b, ptr %dst
+ ret void
+}
+
+declare <32 x i8> @llvm.abs.v32i8(<32 x i8>, i1)
+declare <16 x i16> @llvm.abs.v16i16(<16 x i16>, i1)
+declare <8 x i32> @llvm.abs.v8i32(<8 x i32>, i1)
+declare <4 x i64> @llvm.abs.v4i64(<4 x i64>, i1)
diff --git a/llvm/test/CodeGen/LoongArch/lasx/ir-instruction/adda.ll b/llvm/test/CodeGen/LoongArch/lasx/ir-instruction/adda.ll
index e66a15291fb18..98687755fcfb4 100644
--- a/llvm/test/CodeGen/LoongArch/lasx/ir-instruction/adda.ll
+++ b/llvm/test/CodeGen/LoongArch/lasx/ir-instruction/adda.ll
@@ -7,11 +7,7 @@ define void @vadda_b(ptr %res, ptr %a, ptr %b) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvld $xr0, $a1, 0
; CHECK-NEXT: xvld $xr1, $a2, 0
-; CHECK-NEXT: xvneg.b $xr2, $xr0
-; CHECK-NEXT: xvmax.b $xr0, $xr0, $xr2
-; CHECK-NEXT: xvneg.b $xr2, $xr1
-; CHECK-NEXT: xvmax.b $xr1, $xr1, $xr2
-; CHECK-NEXT: xvadd.b $xr0, $xr0, $xr1
+; CHECK-NEXT: xvadda.b $xr0, $xr0, $xr1
; CHECK-NEXT: xvst $xr0, $a0, 0
; CHECK-NEXT: ret
entry:
@@ -33,11 +29,7 @@ define void @vadda_h(ptr %res, ptr %a, ptr %b) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvld $xr0, $a1, 0
; CHECK-NEXT: xvld $xr1, $a2, 0
-; CHECK-NEXT: xvneg.h $xr2, $xr0
-; CHECK-NEXT: xvmax.h $xr0, $xr0, $xr2
-; CHECK-NEXT: xvneg.h $xr2, $xr1
-; CHECK-NEXT: xvmax.h $xr1, $xr1, $xr2
-; CHECK-NEXT: xvadd.h $xr0, $xr0, $xr1
+; CHECK-NEXT: xvadda.h $xr0, $xr0, $xr1
; CHECK-NEXT: xvst $xr0, $a0, 0
; CHECK-NEXT: ret
entry:
@@ -59,11 +51,7 @@ define void @vadda_w(ptr %res, ptr %a, ptr %b) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvld $xr0, $a1, 0
; CHECK-NEXT: xvld $xr1, $a2, 0
-; CHECK-NEXT: xvneg.w $xr2, $xr0
-; CHECK-NEXT: xvmax.w $xr0, $xr0, $xr2
-; CHECK-NEXT: xvneg.w $xr2, $xr1
-; CHECK-NEXT: xvmax.w $xr1, $xr1, $xr2
-; CHECK-NEXT: xvadd.w $xr0, $xr0, $xr1
+; CHECK-NEXT: xvadda.w $xr0, $xr0, $xr1
; CHECK-NEXT: xvst $xr0, $a0, 0
; CHECK-NEXT: ret
entry:
@@ -85,11 +73,7 @@ define void @vadda_d(ptr %res, ptr %a, ptr %b) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvld $xr0, $a1, 0
; CHECK-NEXT: xvld $xr1, $a2, 0
-; CHECK-NEXT: xvneg.d $xr2, $xr0
-; CHECK-NEXT: xvmax.d $xr0, $xr0, $xr2
-; CHECK-NEXT: xvneg.d $xr2, $xr1
-; CHECK-NEXT: xvmax.d $xr1, $xr1, $xr2
-; CHECK-NEXT: xvadd.d $xr0, $xr0, $xr1
+; CHECK-NEXT: xvadda.d $xr0, $xr0, $xr1
; CHECK-NEXT: xvst $xr0, $a0, 0
; CHECK-NEXT: ret
entry:
diff --git a/llvm/test/CodeGen/LoongArch/lsx/abs.ll b/llvm/test/CodeGen/LoongArch/lsx/abs.ll
new file mode 100644
index 0000000000000..85fe1fe5c0da7
--- /dev/null
+++ b/llvm/test/CodeGen/LoongArch/lsx/abs.ll
@@ -0,0 +1,128 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lsx < %s | FileCheck %s
+; RUN: llc --mtriple=loongarch64 --mattr=+lsx < %s | FileCheck %s
+
+define void @vabs_b(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_b:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vld $vr0, $a1, 0
+; CHECK-NEXT: vneg.b $vr1, $vr0
+; CHECK-NEXT: vmax.b $vr0, $vr0, $vr1
+; CHECK-NEXT: vst $vr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <16 x i8>, ptr %src
+ %b = tail call <16 x i8> @llvm.abs.v16i8(<16 x i8> %a, i1 true)
+ store <16 x i8> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_b_1(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_b_1:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vld $vr0, $a1, 0
+; CHECK-NEXT: vneg.b $vr1, $vr0
+; CHECK-NEXT: vmax.b $vr0, $vr0, $vr1
+; CHECK-NEXT: vst $vr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <16 x i8>, ptr %src
+ %b = tail call <16 x i8> @llvm.abs.v16i8(<16 x i8> %a, i1 false)
+ store <16 x i8> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_h(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_h:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vld $vr0, $a1, 0
+; CHECK-NEXT: vneg.h $vr1, $vr0
+; CHECK-NEXT: vmax.h $vr0, $vr0, $vr1
+; CHECK-NEXT: vst $vr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <8 x i16>, ptr %src
+ %b = tail call <8 x i16> @llvm.abs.v8i16(<8 x i16> %a, i1 true)
+ store <8 x i16> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_h_1(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_h_1:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vld $vr0, $a1, 0
+; CHECK-NEXT: vneg.h $vr1, $vr0
+; CHECK-NEXT: vmax.h $vr0, $vr0, $vr1
+; CHECK-NEXT: vst $vr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <8 x i16>, ptr %src
+ %b = tail call <8 x i16> @llvm.abs.v8i16(<8 x i16> %a, i1 false)
+ store <8 x i16> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_w(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_w:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vld $vr0, $a1, 0
+; CHECK-NEXT: vneg.w $vr1, $vr0
+; CHECK-NEXT: vmax.w $vr0, $vr0, $vr1
+; CHECK-NEXT: vst $vr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <4 x i32>, ptr %src
+ %b = tail call <4 x i32> @llvm.abs.v4i32(<4 x i32> %a, i1 true)
+ store <4 x i32> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_w_1(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_w_1:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vld $vr0, $a1, 0
+; CHECK-NEXT: vneg.w $vr1, $vr0
+; CHECK-NEXT: vmax.w $vr0, $vr0, $vr1
+; CHECK-NEXT: vst $vr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <4 x i32>, ptr %src
+ %b = tail call <4 x i32> @llvm.abs.v4i32(<4 x i32> %a, i1 false)
+ store <4 x i32> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_d(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_d:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vld $vr0, $a1, 0
+; CHECK-NEXT: vneg.d $vr1, $vr0
+; CHECK-NEXT: vmax.d $vr0, $vr0, $vr1
+; CHECK-NEXT: vst $vr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <2 x i64>, ptr %src
+ %b = tail call <2 x i64> @llvm.abs.v2i64(<2 x i64> %a, i1 true)
+ store <2 x i64> %b, ptr %dst
+ ret void
+}
+
+define void @vabs_d_1(ptr %dst, ptr %src) {
+; CHECK-LABEL: vabs_d_1:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vld $vr0, $a1, 0
+; CHECK-NEXT: vneg.d $vr1, $vr0
+; CHECK-NEXT: vmax.d $vr0, $vr0, $vr1
+; CHECK-NEXT: vst $vr0, $a0, 0
+; CHECK-NEXT: ret
+entry:
+ %a = load <2 x i64>, ptr %src
+ %b = tail call <2 x i64> @llvm.abs.v2i64(<2 x i64> %a, i1 false)
+ store <2 x i64> %b, ptr %dst
+ ret void
+}
+
+declare <16 x i8> @llvm.abs.v16i8(<16 x i8>, i1)
+declare <8 x i16> @llvm.abs.v8i16(<8 x i16>, i1)
+declare <4 x i32> @llvm.abs.v4i32(<4 x i32>, i1)
+declare <2 x i64> @llvm.abs.v2i64(<2 x i64>, i1)
diff --git a/llvm/test/CodeGen/LoongArch/lsx/ir-instruction/adda.ll b/llvm/test/CodeGen/LoongArch/lsx/ir-instruction/adda.ll
index 2bd0b597d79ac..34f22e1f6bf45 100644
--- a/llvm/test/CodeGen/LoongArch/lsx/ir-instruction/adda.ll
+++ b/llvm/test/CodeGen/LoongArch/lsx/ir-instruction/adda.ll
@@ -7,11 +7,7 @@ define void @vadda_b(ptr %res, ptr %a, ptr %b) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vld $vr0, $a1, 0
; CHECK-NEXT: vld $vr1, $a2, 0
-; CHECK-NEXT: vneg.b $vr2, $vr0
-; CHECK-NEXT: vmax.b $vr0, $vr0, $vr2
-; CHECK-NEXT: vneg.b $vr2, $vr1
-; CHECK-NEXT: vmax.b $vr1, $vr1, $vr2
-; CHECK-NEXT: vadd.b $vr0, $vr0, $vr1
+; CHECK-NEXT: vadda.b $vr0, $vr0, $vr1
; CHECK-NEXT: vst $vr0, $a0, 0
; CHECK-NEXT: ret
entry:
@@ -33,11 +29,7 @@ define void @vadda_h(ptr %res, ptr %a, ptr %b) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vld $vr0, $a1, 0
; CHECK-NEXT: vld $vr1, $a2, 0
-; CHECK-NEXT: vneg.h $vr2, $vr0
-; CHECK-NEXT: vmax.h $vr0, $vr0, $vr2
-; CHECK-NEXT: vneg.h $vr2, $vr1
-; CHECK-NEXT: vmax.h $vr1, $vr1, $vr2
-; CHECK-NEXT: vadd.h $vr0, $vr0, $vr1
+; CHECK-NEXT: vadda.h $vr0, $vr0, $vr1
; CHECK-NEXT: vst $vr0, $a0, 0
; CHECK-NEXT: ret
entry:
@@ -59,11 +51,7 @@ define void @vadda_w(ptr %res, ptr %a, ptr %b) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vld $vr0, $a1, 0
; CHECK-NEXT: vld $vr1, $a2, 0
-; CHECK-NEXT: vneg.w $vr2, $vr0
-; CHECK-NEXT: vmax.w $vr0, $vr0, $vr2
-; CHECK-NEXT: vneg.w $vr2, $vr1
-; CHECK-NEXT: vmax.w $vr1, $vr1, $vr2
-; CHECK-NEXT: vadd.w $vr0, $vr0, $vr1
+; CHECK-NEXT: vadda.w $vr0, $vr0, $vr1
; CHECK-NEXT: vst $vr0, $a0, 0
; CHECK-NEXT: ret
entry:
@@ -85,11 +73,7 @@ define void @vadda_d(ptr %res, ptr %a, ptr %b) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vld $vr0, $a1, 0
; CHECK-NEXT: vld $vr1, $a2, 0
-; CHECK-NEXT: vneg.d $vr2, $vr0
-; CHECK-NEXT: vmax.d $vr0, $vr0, $vr2
-; CHECK-NEXT: vneg.d $vr2, $vr1
-; CHECK-NEXT: vmax.d $vr1, $vr1, $vr2
-; CHECK-NEXT: vadd.d $vr0, $vr0, $vr1
+; CHECK-NEXT: vadda.d $vr0, $vr0, $vr1
; CHECK-NEXT: vst $vr0, $a0, 0
; CHECK-NEXT: ret
entry:
More information about the llvm-commits
mailing list