[RISCV] Use mask undisturbed policy when silencing sNans for strict rounding ops. (#93356)
The elements that aren't sNans need to get passed through this fadd
instruction unchanged. With the agnostic mask policy they might be
forced to all ones.
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-ftrunc-constrained-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-ftrunc-constrained-sdnode.ll
index f165814..eac2645 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-ftrunc-constrained-sdnode.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-ftrunc-constrained-sdnode.ll
@@ -7,13 +7,14 @@
define <1 x half> @trunc_v1f16(<1 x half> %x) strictfp {
; CHECK-LABEL: trunc_v1f16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma
+; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI0_0)
; CHECK-NEXT: flh fa5, %lo(.LCPI0_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v9, v8
; CHECK-NEXT: vmflt.vf v0, v9, fa5
+; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
@@ -27,13 +28,14 @@
define <2 x half> @trunc_v2f16(<2 x half> %x) strictfp {
; CHECK-LABEL: trunc_v2f16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
+; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI1_0)
; CHECK-NEXT: flh fa5, %lo(.LCPI1_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v9, v8
; CHECK-NEXT: vmflt.vf v0, v9, fa5
+; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
@@ -47,13 +49,14 @@
define <4 x half> @trunc_v4f16(<4 x half> %x) strictfp {
; CHECK-LABEL: trunc_v4f16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI2_0)
; CHECK-NEXT: flh fa5, %lo(.LCPI2_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v9, v8
; CHECK-NEXT: vmflt.vf v0, v9, fa5
+; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
@@ -67,13 +70,14 @@
define <8 x half> @trunc_v8f16(<8 x half> %x) strictfp {
; CHECK-LABEL: trunc_v8f16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI3_0)
; CHECK-NEXT: flh fa5, %lo(.LCPI3_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v9, v8
; CHECK-NEXT: vmflt.vf v0, v9, fa5
+; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, mu
@@ -87,13 +91,14 @@
define <16 x half> @trunc_v16f16(<16 x half> %x) strictfp {
; CHECK-LABEL: trunc_v16f16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, ma
+; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI4_0)
; CHECK-NEXT: flh fa5, %lo(.LCPI4_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v10, v8
; CHECK-NEXT: vmflt.vf v0, v10, fa5
+; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, mu
@@ -108,13 +113,14 @@
; CHECK-LABEL: trunc_v32f16:
; CHECK: # %bb.0:
; CHECK-NEXT: li a0, 32
-; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI5_0)
; CHECK-NEXT: flh fa5, %lo(.LCPI5_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v12, v8
; CHECK-NEXT: vmflt.vf v0, v12, fa5
+; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, mu
@@ -128,13 +134,14 @@
define <1 x float> @trunc_v1f32(<1 x float> %x) strictfp {
; CHECK-LABEL: trunc_v1f32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma
+; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v9, v8
; CHECK-NEXT: lui a0, 307200
; CHECK-NEXT: fmv.w.x fa5, a0
; CHECK-NEXT: vmflt.vf v0, v9, fa5
+; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
@@ -148,13 +155,14 @@
define <2 x float> @trunc_v2f32(<2 x float> %x) strictfp {
; CHECK-LABEL: trunc_v2f32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v9, v8
; CHECK-NEXT: lui a0, 307200
; CHECK-NEXT: fmv.w.x fa5, a0
; CHECK-NEXT: vmflt.vf v0, v9, fa5
+; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
@@ -168,13 +176,14 @@
define <4 x float> @trunc_v4f32(<4 x float> %x) strictfp {
; CHECK-LABEL: trunc_v4f32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v9, v8
; CHECK-NEXT: lui a0, 307200
; CHECK-NEXT: fmv.w.x fa5, a0
; CHECK-NEXT: vmflt.vf v0, v9, fa5
+; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu
@@ -188,13 +197,14 @@
define <8 x float> @trunc_v8f32(<8 x float> %x) strictfp {
; CHECK-LABEL: trunc_v8f32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
+; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v10, v8
; CHECK-NEXT: lui a0, 307200
; CHECK-NEXT: fmv.w.x fa5, a0
; CHECK-NEXT: vmflt.vf v0, v10, fa5
+; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu
@@ -208,13 +218,14 @@
define <16 x float> @trunc_v16f32(<16 x float> %x) strictfp {
; CHECK-LABEL: trunc_v16f32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v12, v8
; CHECK-NEXT: lui a0, 307200
; CHECK-NEXT: fmv.w.x fa5, a0
; CHECK-NEXT: vmflt.vf v0, v12, fa5
+; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu
@@ -228,13 +239,14 @@
define <1 x double> @trunc_v1f64(<1 x double> %x) strictfp {
; CHECK-LABEL: trunc_v1f64:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
+; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI11_0)
; CHECK-NEXT: fld fa5, %lo(.LCPI11_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v9, v8
; CHECK-NEXT: vmflt.vf v0, v9, fa5
+; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu
@@ -248,13 +260,14 @@
define <2 x double> @trunc_v2f64(<2 x double> %x) strictfp {
; CHECK-LABEL: trunc_v2f64:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma
+; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI12_0)
; CHECK-NEXT: fld fa5, %lo(.LCPI12_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v9, v8
; CHECK-NEXT: vmflt.vf v0, v9, fa5
+; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu
@@ -268,13 +281,14 @@
define <4 x double> @trunc_v4f64(<4 x double> %x) strictfp {
; CHECK-LABEL: trunc_v4f64:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, ma
+; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI13_0)
; CHECK-NEXT: fld fa5, %lo(.LCPI13_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v10, v8
; CHECK-NEXT: vmflt.vf v0, v10, fa5
+; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu
@@ -288,13 +302,14 @@
define <8 x double> @trunc_v8f64(<8 x double> %x) strictfp {
; CHECK-LABEL: trunc_v8f64:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, ma
+; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; CHECK-NEXT: vmfne.vv v0, v8, v8
; CHECK-NEXT: lui a0, %hi(.LCPI14_0)
; CHECK-NEXT: fld fa5, %lo(.LCPI14_0)(a0)
; CHECK-NEXT: vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT: vfabs.v v12, v8
; CHECK-NEXT: vmflt.vf v0, v12, fa5
+; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, ma
; CHECK-NEXT: vfcvt.rtz.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu
