[LoongArch] Pre-commit tests for saturation sadd/ssub/uadd/usub intrinsics

llvm/test/CodeGen/LoongArch/lasx/ir-instruction/sadd-sat.ll

@@ -0,0 +1,81 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lasx < %s | FileCheck %s --check-prefixes=CHECK,LA32
+; RUN: llc -mtriple=loongarch64 -mattr=+lasx < %s | FileCheck %s --check-prefixes=CHECK,LA64
+
+define <32 x i8> @xvsadd_b(<32 x i8> %a, <32 x i8> %b) {
+; CHECK-LABEL: xvsadd_b:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvadd.b $xr2, $xr0, $xr1
+; CHECK-NEXT:    xvslt.b $xr0, $xr2, $xr0
+; CHECK-NEXT:    xvslti.b $xr1, $xr1, 0
+; CHECK-NEXT:    xvxor.v $xr0, $xr1, $xr0
+; CHECK-NEXT:    xvsrai.b $xr1, $xr2, 7
+; CHECK-NEXT:    xvbitrevi.b $xr1, $xr1, 7
+; CHECK-NEXT:    xvbitsel.v $xr0, $xr2, $xr1, $xr0
+; CHECK-NEXT:    ret
+  %ret = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> %a, <32 x i8> %b)
+  ret <32 x i8> %ret
+}
+
+define <16 x i16> @xvsadd_h(<16 x i16> %a, <16 x i16> %b) {
+; CHECK-LABEL: xvsadd_h:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvadd.h $xr2, $xr0, $xr1
+; CHECK-NEXT:    xvslt.h $xr0, $xr2, $xr0
+; CHECK-NEXT:    xvslti.h $xr1, $xr1, 0
+; CHECK-NEXT:    xvxor.v $xr0, $xr1, $xr0
+; CHECK-NEXT:    xvsrai.h $xr1, $xr2, 15
+; CHECK-NEXT:    xvbitrevi.h $xr1, $xr1, 15
+; CHECK-NEXT:    xvbitsel.v $xr0, $xr2, $xr1, $xr0
+; CHECK-NEXT:    ret
+  %ret = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> %a, <16 x i16> %b)
+  ret <16 x i16> %ret
+}
+
+define <8 x i32> @xvsadd_w(<8 x i32> %a, <8 x i32> %b) {
+; CHECK-LABEL: xvsadd_w:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvadd.w $xr2, $xr0, $xr1
+; CHECK-NEXT:    xvslt.w $xr0, $xr2, $xr0
+; CHECK-NEXT:    xvslti.w $xr1, $xr1, 0
+; CHECK-NEXT:    xvxor.v $xr0, $xr1, $xr0
+; CHECK-NEXT:    xvsrai.w $xr1, $xr2, 31
+; CHECK-NEXT:    xvbitrevi.w $xr1, $xr1, 31
+; CHECK-NEXT:    xvbitsel.v $xr0, $xr2, $xr1, $xr0
+; CHECK-NEXT:    ret
+  %ret = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> %a, <8 x i32> %b)
+  ret <8 x i32> %ret
+}
+
+define <4 x i64> @xvsadd_d(<4 x i64> %a, <4 x i64> %b) {
+; LA32-LABEL: xvsadd_d:
+; LA32:       # %bb.0:
+; LA32-NEXT:    xvadd.d $xr2, $xr0, $xr1
+; LA32-NEXT:    xvslt.d $xr0, $xr2, $xr0
+; LA32-NEXT:    pcalau12i $a0, %pc_hi20(.LCPI3_0)
+; LA32-NEXT:    xvld $xr3, $a0, %pc_lo12(.LCPI3_0)
+; LA32-NEXT:    xvslti.d $xr1, $xr1, 0
+; LA32-NEXT:    xvxor.v $xr0, $xr1, $xr0
+; LA32-NEXT:    xvsrai.d $xr1, $xr2, 63
+; LA32-NEXT:    xvxor.v $xr1, $xr1, $xr3
+; LA32-NEXT:    xvbitsel.v $xr0, $xr2, $xr1, $xr0
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: xvsadd_d:
+; LA64:       # %bb.0:
+; LA64-NEXT:    xvadd.d $xr2, $xr0, $xr1
+; LA64-NEXT:    xvslt.d $xr0, $xr2, $xr0
+; LA64-NEXT:    xvslti.d $xr1, $xr1, 0
+; LA64-NEXT:    xvxor.v $xr0, $xr1, $xr0
+; LA64-NEXT:    xvsrai.d $xr1, $xr2, 63
+; LA64-NEXT:    xvbitrevi.d $xr1, $xr1, 63
+; LA64-NEXT:    xvbitsel.v $xr0, $xr2, $xr1, $xr0
+; LA64-NEXT:    ret
+  %ret = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> %a, <4 x i64> %b)
+  ret <4 x i64> %ret
+}
+
+declare <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8>, <32 x i8>)
+declare <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16>, <16 x i16>)
+declare <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32>, <8 x i32>)
+declare <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64>, <4 x i64>)

llvm/test/CodeGen/LoongArch/lasx/ir-instruction/ssub-sat.ll

@@ -0,0 +1,86 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lasx < %s | FileCheck %s --check-prefixes=CHECK,LA32
+; RUN: llc -mtriple=loongarch64 -mattr=+lasx < %s | FileCheck %s --check-prefixes=CHECK,LA64
+
+define <32 x i8> @xvssub_b(<32 x i8> %a, <32 x i8> %b) {
+; CHECK-LABEL: xvssub_b:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvrepli.b $xr2, 0
+; CHECK-NEXT:    xvslt.b $xr2, $xr2, $xr1
+; CHECK-NEXT:    xvsub.b $xr1, $xr0, $xr1
+; CHECK-NEXT:    xvslt.b $xr0, $xr1, $xr0
+; CHECK-NEXT:    xvxor.v $xr0, $xr2, $xr0
+; CHECK-NEXT:    xvsrai.b $xr2, $xr1, 7
+; CHECK-NEXT:    xvbitrevi.b $xr2, $xr2, 7
+; CHECK-NEXT:    xvbitsel.v $xr0, $xr1, $xr2, $xr0
+; CHECK-NEXT:    ret
+  %ret = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> %a, <32 x i8> %b)
+  ret <32 x i8> %ret
+}
+
+define <16 x i16> @xvssub_h(<16 x i16> %a, <16 x i16> %b) {
+; CHECK-LABEL: xvssub_h:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvrepli.b $xr2, 0
+; CHECK-NEXT:    xvslt.h $xr2, $xr2, $xr1
+; CHECK-NEXT:    xvsub.h $xr1, $xr0, $xr1
+; CHECK-NEXT:    xvslt.h $xr0, $xr1, $xr0
+; CHECK-NEXT:    xvxor.v $xr0, $xr2, $xr0
+; CHECK-NEXT:    xvsrai.h $xr2, $xr1, 15
+; CHECK-NEXT:    xvbitrevi.h $xr2, $xr2, 15
+; CHECK-NEXT:    xvbitsel.v $xr0, $xr1, $xr2, $xr0
+; CHECK-NEXT:    ret
+  %ret = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> %a, <16 x i16> %b)
+  ret <16 x i16> %ret
+}
+
+define <8 x i32> @xvssub_w(<8 x i32> %a, <8 x i32> %b) {
+; CHECK-LABEL: xvssub_w:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvrepli.b $xr2, 0
+; CHECK-NEXT:    xvslt.w $xr2, $xr2, $xr1
+; CHECK-NEXT:    xvsub.w $xr1, $xr0, $xr1
+; CHECK-NEXT:    xvslt.w $xr0, $xr1, $xr0
+; CHECK-NEXT:    xvxor.v $xr0, $xr2, $xr0
+; CHECK-NEXT:    xvsrai.w $xr2, $xr1, 31
+; CHECK-NEXT:    xvbitrevi.w $xr2, $xr2, 31
+; CHECK-NEXT:    xvbitsel.v $xr0, $xr1, $xr2, $xr0
+; CHECK-NEXT:    ret
+  %ret = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> %a, <8 x i32> %b)
+  ret <8 x i32> %ret
+}
+
+define <4 x i64> @xvssub_d(<4 x i64> %a, <4 x i64> %b) {
+; LA32-LABEL: xvssub_d:
+; LA32:       # %bb.0:
+; LA32-NEXT:    xvrepli.b $xr2, 0
+; LA32-NEXT:    xvslt.d $xr2, $xr2, $xr1
+; LA32-NEXT:    xvsub.d $xr1, $xr0, $xr1
+; LA32-NEXT:    pcalau12i $a0, %pc_hi20(.LCPI3_0)
+; LA32-NEXT:    xvld $xr3, $a0, %pc_lo12(.LCPI3_0)
+; LA32-NEXT:    xvslt.d $xr0, $xr1, $xr0
+; LA32-NEXT:    xvxor.v $xr0, $xr2, $xr0
+; LA32-NEXT:    xvsrai.d $xr2, $xr1, 63
+; LA32-NEXT:    xvxor.v $xr2, $xr2, $xr3
+; LA32-NEXT:    xvbitsel.v $xr0, $xr1, $xr2, $xr0
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: xvssub_d:
+; LA64:       # %bb.0:
+; LA64-NEXT:    xvrepli.b $xr2, 0
+; LA64-NEXT:    xvslt.d $xr2, $xr2, $xr1
+; LA64-NEXT:    xvsub.d $xr1, $xr0, $xr1
+; LA64-NEXT:    xvslt.d $xr0, $xr1, $xr0
+; LA64-NEXT:    xvxor.v $xr0, $xr2, $xr0
+; LA64-NEXT:    xvsrai.d $xr2, $xr1, 63
+; LA64-NEXT:    xvbitrevi.d $xr2, $xr2, 63
+; LA64-NEXT:    xvbitsel.v $xr0, $xr1, $xr2, $xr0
+; LA64-NEXT:    ret
+  %ret = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> %a, <4 x i64> %b)
+  ret <4 x i64> %ret
+}
+
+declare <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8>, <32 x i8>)
+declare <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16>, <16 x i16>)
+declare <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32>, <8 x i32>)
+declare <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64>, <4 x i64>)

llvm/test/CodeGen/LoongArch/lasx/ir-instruction/uadd-sat.ll

@@ -0,0 +1,55 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lasx < %s | FileCheck %s
+; RUN: llc -mtriple=loongarch64 -mattr=+lasx < %s | FileCheck %s
+
+define <32 x i8> @xvuadd_b(<32 x i8> %a, <32 x i8> %b) {
+; CHECK-LABEL: xvuadd_b:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvxori.b $xr2, $xr1, 255
+; CHECK-NEXT:    xvmin.bu $xr0, $xr0, $xr2
+; CHECK-NEXT:    xvadd.b $xr0, $xr0, $xr1
+; CHECK-NEXT:    ret
+  %ret = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> %a, <32 x i8> %b)
+  ret <32 x i8> %ret
+}
+
+define <16 x i16> @xvuadd_h(<16 x i16> %a, <16 x i16> %b) {
+; CHECK-LABEL: xvuadd_h:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvrepli.b $xr2, -1
+; CHECK-NEXT:    xvxor.v $xr2, $xr1, $xr2
+; CHECK-NEXT:    xvmin.hu $xr0, $xr0, $xr2
+; CHECK-NEXT:    xvadd.h $xr0, $xr0, $xr1
+; CHECK-NEXT:    ret
+  %ret = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> %a, <16 x i16> %b)
+  ret <16 x i16> %ret
+}
+
+define <8 x i32> @xvuadd_w(<8 x i32> %a, <8 x i32> %b) {
+; CHECK-LABEL: xvuadd_w:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvrepli.b $xr2, -1
+; CHECK-NEXT:    xvxor.v $xr2, $xr1, $xr2
+; CHECK-NEXT:    xvmin.wu $xr0, $xr0, $xr2
+; CHECK-NEXT:    xvadd.w $xr0, $xr0, $xr1
+; CHECK-NEXT:    ret
+  %ret = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> %a, <8 x i32> %b)
+  ret <8 x i32> %ret
+}
+
+define <4 x i64> @xvuadd_d(<4 x i64> %a, <4 x i64> %b) {
+; CHECK-LABEL: xvuadd_d:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvrepli.b $xr2, -1
+; CHECK-NEXT:    xvxor.v $xr2, $xr1, $xr2
+; CHECK-NEXT:    xvmin.du $xr0, $xr0, $xr2
+; CHECK-NEXT:    xvadd.d $xr0, $xr0, $xr1
+; CHECK-NEXT:    ret
+  %ret = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> %a, <4 x i64> %b)
+  ret <4 x i64> %ret
+}
+
+declare <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8>, <32 x i8>)
+declare <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16>, <16 x i16>)
+declare <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32>, <8 x i32>)
+declare <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64>, <4 x i64>)

llvm/test/CodeGen/LoongArch/lasx/ir-instruction/usub-sat.ll

@@ -0,0 +1,48 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lasx < %s | FileCheck %s
+; RUN: llc -mtriple=loongarch64 -mattr=+lasx < %s | FileCheck %s
+
+define <32 x i8> @xvusub_b(<32 x i8> %a, <32 x i8> %b) {
+; CHECK-LABEL: xvusub_b:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvmax.bu $xr0, $xr0, $xr1
+; CHECK-NEXT:    xvsub.b $xr0, $xr0, $xr1
+; CHECK-NEXT:    ret
+  %ret = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> %a, <32 x i8> %b)
+  ret <32 x i8> %ret
+}
+
+define <16 x i16> @xvusub_h(<16 x i16> %a, <16 x i16> %b) {
+; CHECK-LABEL: xvusub_h:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvmax.hu $xr0, $xr0, $xr1
+; CHECK-NEXT:    xvsub.h $xr0, $xr0, $xr1
+; CHECK-NEXT:    ret
+  %ret = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> %a, <16 x i16> %b)
+  ret <16 x i16> %ret
+}
+
+define <8 x i32> @xvusub_w(<8 x i32> %a, <8 x i32> %b) {
+; CHECK-LABEL: xvusub_w:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvmax.wu $xr0, $xr0, $xr1
+; CHECK-NEXT:    xvsub.w $xr0, $xr0, $xr1
+; CHECK-NEXT:    ret
+  %ret = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> %a, <8 x i32> %b)
+  ret <8 x i32> %ret
+}
+
+define <4 x i64> @xvusub_d(<4 x i64> %a, <4 x i64> %b) {
+; CHECK-LABEL: xvusub_d:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xvmax.du $xr0, $xr0, $xr1
+; CHECK-NEXT:    xvsub.d $xr0, $xr0, $xr1
+; CHECK-NEXT:    ret
+  %ret = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> %a, <4 x i64> %b)
+  ret <4 x i64> %ret
+}
+
+declare <32 x i8> @llvm.usub.sat.v32i8(<32 x i8>, <32 x i8>)
+declare <16 x i16> @llvm.usub.sat.v16i16(<16 x i16>, <16 x i16>)
+declare <8 x i32> @llvm.usub.sat.v8i32(<8 x i32>, <8 x i32>)
+declare <4 x i64> @llvm.usub.sat.v4i64(<4 x i64>, <4 x i64>)

llvm/test/CodeGen/LoongArch/lsx/ir-instruction/sadd-sat.ll

@@ -0,0 +1,81 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lsx < %s | FileCheck %s --check-prefixes=CHECK,LA32
+; RUN: llc -mtriple=loongarch64 -mattr=+lsx < %s | FileCheck %s --check-prefixes=CHECK,LA64
+
+define <16 x i8> @vsadd_b(<16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: vsadd_b:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vadd.b $vr2, $vr0, $vr1
+; CHECK-NEXT:    vslt.b $vr0, $vr2, $vr0
+; CHECK-NEXT:    vslti.b $vr1, $vr1, 0
+; CHECK-NEXT:    vxor.v $vr0, $vr1, $vr0
+; CHECK-NEXT:    vsrai.b $vr1, $vr2, 7
+; CHECK-NEXT:    vbitrevi.b $vr1, $vr1, 7
+; CHECK-NEXT:    vbitsel.v $vr0, $vr2, $vr1, $vr0
+; CHECK-NEXT:    ret
+  %ret = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> %a, <16 x i8> %b)
+  ret <16 x i8> %ret
+}
+
+define <8 x i16> @vsadd_h(<8 x i16> %a, <8 x i16> %b) {
+; CHECK-LABEL: vsadd_h:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vadd.h $vr2, $vr0, $vr1
+; CHECK-NEXT:    vslt.h $vr0, $vr2, $vr0
+; CHECK-NEXT:    vslti.h $vr1, $vr1, 0
+; CHECK-NEXT:    vxor.v $vr0, $vr1, $vr0
+; CHECK-NEXT:    vsrai.h $vr1, $vr2, 15
+; CHECK-NEXT:    vbitrevi.h $vr1, $vr1, 15
+; CHECK-NEXT:    vbitsel.v $vr0, $vr2, $vr1, $vr0
+; CHECK-NEXT:    ret
+  %ret = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> %a, <8 x i16> %b)
+  ret <8 x i16> %ret
+}
+
+define <4 x i32> @vsadd_w(<4 x i32> %a, <4 x i32> %b) {
+; CHECK-LABEL: vsadd_w:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vadd.w $vr2, $vr0, $vr1
+; CHECK-NEXT:    vslt.w $vr0, $vr2, $vr0
+; CHECK-NEXT:    vslti.w $vr1, $vr1, 0
+; CHECK-NEXT:    vxor.v $vr0, $vr1, $vr0
+; CHECK-NEXT:    vsrai.w $vr1, $vr2, 31
+; CHECK-NEXT:    vbitrevi.w $vr1, $vr1, 31
+; CHECK-NEXT:    vbitsel.v $vr0, $vr2, $vr1, $vr0
+; CHECK-NEXT:    ret
+  %ret = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> %a, <4 x i32> %b)
+  ret <4 x i32> %ret
+}
+
+define <2 x i64> @vsadd_d(<2 x i64> %a, <2 x i64> %b) {
+; LA32-LABEL: vsadd_d:
+; LA32:       # %bb.0:
+; LA32-NEXT:    vadd.d $vr2, $vr0, $vr1
+; LA32-NEXT:    vslt.d $vr0, $vr2, $vr0
+; LA32-NEXT:    pcalau12i $a0, %pc_hi20(.LCPI3_0)
+; LA32-NEXT:    vld $vr3, $a0, %pc_lo12(.LCPI3_0)
+; LA32-NEXT:    vslti.d $vr1, $vr1, 0
+; LA32-NEXT:    vxor.v $vr0, $vr1, $vr0
+; LA32-NEXT:    vsrai.d $vr1, $vr2, 63
+; LA32-NEXT:    vxor.v $vr1, $vr1, $vr3
+; LA32-NEXT:    vbitsel.v $vr0, $vr2, $vr1, $vr0
+; LA32-NEXT:    ret
+;
+; LA64-LABEL: vsadd_d:
+; LA64:       # %bb.0:
+; LA64-NEXT:    vadd.d $vr2, $vr0, $vr1
+; LA64-NEXT:    vslt.d $vr0, $vr2, $vr0
+; LA64-NEXT:    vslti.d $vr1, $vr1, 0
+; LA64-NEXT:    vxor.v $vr0, $vr1, $vr0
+; LA64-NEXT:    vsrai.d $vr1, $vr2, 63
+; LA64-NEXT:    vbitrevi.d $vr1, $vr1, 63
+; LA64-NEXT:    vbitsel.v $vr0, $vr2, $vr1, $vr0
+; LA64-NEXT:    ret
+  %ret = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> %a, <2 x i64> %b)
+  ret <2 x i64> %ret
+}
+
+declare <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8>, <16 x i8>)
+declare <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16>, <8 x i16>)
+declare <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32>, <4 x i32>)
+declare <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64>, <2 x i64>)