[llvm] [RISCV] Lower scalar_to_vector for supported FP types (PR #114340)

[Luke Lau via llvm-commits]

================
@@ -9,36 +9,54 @@ define <4 x float> @foo(ptr %0) nounwind {
 ; CHECK-NEXT:    sd s0, 32(sp) # 8-byte Folded Spill
 ; CHECK-NEXT:    sd s1, 24(sp) # 8-byte Folded Spill
 ; CHECK-NEXT:    sd s2, 16(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    slli a1, a1, 1
+; CHECK-NEXT:    sub sp, sp, a1
 ; CHECK-NEXT:    lhu s0, 0(a0)
 ; CHECK-NEXT:    lhu s1, 2(a0)
 ; CHECK-NEXT:    lhu s2, 4(a0)
 ; CHECK-NEXT:    lhu a0, 6(a0)
 ; CHECK-NEXT:    fmv.w.x fa0, a0
 ; CHECK-NEXT:    call __extendhfsf2
-; CHECK-NEXT:    fsw fa0, 4(sp)
-; CHECK-NEXT:    fmv.w.x fa0, s2
+; CHECK-NEXT:    fmv.w.x fa5, s2
+; CHECK-NEXT:    vsetivli zero, 1, e32, m1, ta, ma
+; CHECK-NEXT:    vfmv.s.f v8, fa0
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vs1r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    fmv.s fa0, fa5
 ; CHECK-NEXT:    call __extendhfsf2
-; CHECK-NEXT:    fsw fa0, 12(sp)
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT:    vfmv.s.f v8, fa0
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl1r.v v9, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vslideup.vi v8, v9, 1
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vs1r.v v8, (a0) # Unknown-size Folded Spill
 ; CHECK-NEXT:    fmv.w.x fa0, s1
 ; CHECK-NEXT:    call __extendhfsf2
-; CHECK-NEXT:    fsw fa0, 8(sp)
-; CHECK-NEXT:    fmv.w.x fa0, s0
+; CHECK-NEXT:    fmv.w.x fa5, s0
+; CHECK-NEXT:    vsetivli zero, 1, e32, m1, ta, ma
+; CHECK-NEXT:    vfmv.s.f v8, fa0
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vs1r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    fmv.s fa0, fa5
 ; CHECK-NEXT:    call __extendhfsf2
-; CHECK-NEXT:    fsw fa0, 0(sp)
-; CHECK-NEXT:    addi a0, sp, 4
-; CHECK-NEXT:    vsetivli zero, 1, e32, mf2, ta, ma
-; CHECK-NEXT:    vle32.v v9, (a0)
-; CHECK-NEXT:    addi a0, sp, 12
-; CHECK-NEXT:    vle32.v v10, (a0)
-; CHECK-NEXT:    addi a0, sp, 8
-; CHECK-NEXT:    vle32.v v11, (a0)
-; CHECK-NEXT:    mv a0, sp
-; CHECK-NEXT:    vle32.v v8, (a0)
 ; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
-; CHECK-NEXT:    vslideup.vi v10, v9, 1
-; CHECK-NEXT:    vslideup.vi v8, v11, 1
+; CHECK-NEXT:    vfmv.s.f v8, fa0
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl1r.v v9, (a0) # Unknown-size Folded Reload
----------------
lukel97 wrote:

We're now spilling and reloading the vector due to the ABI but at least it gets rid of the one element unit strided loads.

https://github.com/llvm/llvm-project/pull/114340