Automerge: [LoongArch] Fix fp_to_uint/fp_to_sint conversion errors for lasx (#137129)

Prvious `fp_to_uint/fp_to_sint` patterns for `v4f64 -> v4i32` are wrong.
Conversion error was triggered after pr
llvm/llvm-project#126456.

(cherry picked from commit b5c7724)

Author: tangaac

llvm/lib/Target/LoongArch/LoongArchLASXInstrInfo.td

@@ -1792,24 +1792,24 @@ def : Pat<(v4f32 (uint_to_fp v4i64:$vj)),
 // XVFTINTRZ_{W_S/L_D}
 def : Pat<(v8i32 (fp_to_sint v8f32:$vj)), (XVFTINTRZ_W_S v8f32:$vj)>;
 def : Pat<(v4i64 (fp_to_sint v4f64:$vj)), (XVFTINTRZ_L_D v4f64:$vj)>;
-def : Pat<(v4i64 (fp_to_sint v4f32:$vj)),
-          (VEXT2XV_D_W (SUBREG_TO_REG (i64 0), (VFTINTRZ_W_S v4f32:$vj),
-                                      sub_128))>;
-def : Pat<(v4i32 (fp_to_sint (v4f64 LASX256:$vj))),
-          (EXTRACT_SUBREG (XVFTINTRZ_W_S (XVFCVT_S_D (XVPERMI_D v4f64:$vj, 238),
-                                                     v4f64:$vj)),
-                          sub_128)>;
+def : Pat<(v4i64(fp_to_sint v4f32:$vj)), (VEXT2XV_D_W(SUBREG_TO_REG(i64 0),
+                                             (VFTINTRZ_W_S v4f32:$vj),
+                                             sub_128))>;
+def : Pat<(v4i32(fp_to_sint v4f64:$vj)),
+          (EXTRACT_SUBREG(XVPICKEV_W(XVPERMI_D(XVFTINTRZ_L_D v4f64:$vj), 238),
+               (XVFTINTRZ_L_D v4f64:$vj)),
+              sub_128)>;
 
 // XVFTINTRZ_{W_SU/L_DU}
 def : Pat<(v8i32 (fp_to_uint v8f32:$vj)), (XVFTINTRZ_WU_S v8f32:$vj)>;
 def : Pat<(v4i64 (fp_to_uint v4f64:$vj)), (XVFTINTRZ_LU_D v4f64:$vj)>;
-def : Pat<(v4i64 (fp_to_uint v4f32:$vj)),
-          (VEXT2XV_DU_WU (SUBREG_TO_REG (i64 0), (VFTINTRZ_WU_S v4f32:$vj),
-                                        sub_128))>;
-def : Pat<(v4i32 (fp_to_uint (v4f64 LASX256:$vj))),
-          (EXTRACT_SUBREG (XVFTINTRZ_W_S (XVFCVT_S_D (XVPERMI_D v4f64:$vj, 238),
-                                                     v4f64:$vj)),
-                          sub_128)>;
+def : Pat<(v4i64(fp_to_uint v4f32:$vj)), (VEXT2XV_DU_WU(SUBREG_TO_REG(i64 0),
+                                             (VFTINTRZ_WU_S v4f32:$vj),
+                                             sub_128))>;
+def : Pat<(v4i32(fp_to_uint v4f64:$vj)),
+          (EXTRACT_SUBREG(XVPICKEV_W(XVPERMI_D(XVFTINTRZ_LU_D v4f64:$vj), 238),
+               (XVFTINTRZ_LU_D v4f64:$vj)),
+              sub_128)>;
 
 // XVPERMI_Q
 foreach vt = [v32i8, v16i16, v8i32, v4i64, v8f32, v4f64] in

llvm/test/CodeGen/LoongArch/lasx/ir-instruction/fptosi.ll

@@ -31,9 +31,9 @@ define void @fptosi_v4f64_v4i32(ptr %res, ptr %in){
 ; CHECK-LABEL: fptosi_v4f64_v4i32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    xvld $xr0, $a1, 0
+; CHECK-NEXT:    xvftintrz.l.d $xr0, $xr0
 ; CHECK-NEXT:    xvpermi.d $xr1, $xr0, 238
-; CHECK-NEXT:    xvfcvt.s.d $xr0, $xr1, $xr0
-; CHECK-NEXT:    xvftintrz.w.s $xr0, $xr0
+; CHECK-NEXT:    xvpickev.w $xr0, $xr1, $xr0
 ; CHECK-NEXT:    vst $vr0, $a0, 0
 ; CHECK-NEXT:    ret
   %v0 = load <4 x double>, ptr %in

llvm/test/CodeGen/LoongArch/lasx/ir-instruction/fptoui.ll

@@ -31,9 +31,9 @@ define void @fptoui_v4f64_v4i32(ptr %res, ptr %in){
 ; CHECK-LABEL: fptoui_v4f64_v4i32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    xvld $xr0, $a1, 0
+; CHECK-NEXT:    xvftintrz.lu.d $xr0, $xr0
 ; CHECK-NEXT:    xvpermi.d $xr1, $xr0, 238
-; CHECK-NEXT:    xvfcvt.s.d $xr0, $xr1, $xr0
-; CHECK-NEXT:    xvftintrz.w.s $xr0, $xr0
+; CHECK-NEXT:    xvpickev.w $xr0, $xr1, $xr0
 ; CHECK-NEXT:    vst $vr0, $a0, 0
 ; CHECK-NEXT:    ret
   %v0 = load <4 x double>, ptr %in