[SystemZ] Consider VST/VL as SimpleBDXStore/Load

Previously VST and VL were not considered "simple" BDX stores and loads,
leading to, among other things, some opportunities for mvc optimization
to be missed.

This commit addresses this and updates some tests to account for additional
mvc instructions being emitted.

This is observed to have a neutral or slightly beneficial effect
performance-wise.

Author: dominik-steenken

llvm/lib/Target/SystemZ/SystemZInstrVector.td

@@ -105,7 +105,8 @@ let Predicates = [FeatureVector] in {
 
 let Predicates = [FeatureVector] in {
   // Load.
-  defm VL : UnaryVRXAlign<"vl", 0xE706>;
+  let SimpleBDXLoad = 1 in
+      defm VL : UnaryVRXAlign<"vl", 0xE706>;
 
   // Load to block boundary.  The number of loaded bytes is only known
   // at run time.  The instruction is really polymorphic, but v128b matches
@@ -213,7 +214,8 @@ defm : ReplicatePeephole<VLREPG, v2f64, z_load, f64>;
 
 let Predicates = [FeatureVector] in {
   // Store.
-  defm VST : StoreVRXAlign<"vst", 0xE70E>;
+  let SimpleBDXStore = 1 in
+      defm VST : StoreVRXAlign<"vst", 0xE70E>;
 
   // Store with length.  The number of stored bytes is only known at run time.
   def VSTL : StoreLengthVRSb<"vstl", 0xE73F, int_s390_vstl, 0>;

llvm/test/CodeGen/SystemZ/vector-constrained-fp-intrinsics.ll

@@ -440,10 +440,9 @@ define void @constrained_vector_frem_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    ld %f0, 0(%r1)
 ; SZ13-NEXT:    ldr %f2, %f8
 ; SZ13-NEXT:    brasl %r14, fmod@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -1473,11 +1472,10 @@ define void @constrained_vector_pow_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    ldr %f2, %f9
 ; SZ13-NEXT:    brasl %r14, pow@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 200(%r15) # 8-byte Reload
 ; SZ13-NEXT:    ld %f9, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 312(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -1829,9 +1827,8 @@ define void @constrained_vector_powi_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    ld %f0, 0(%r1)
 ; SZ13-NEXT:    lghi %r2, 3
 ; SZ13-NEXT:    brasl %r14, __powidf2@PLT
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
 ; SZ13-NEXT:    lmg %r13, %r15, 280(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -2155,10 +2152,9 @@ define void @constrained_vector_sin_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    vst %v0, 160(%r15), 3 # 16-byte Folded Spill
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    brasl %r14, sin@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -2472,10 +2468,9 @@ define void @constrained_vector_cos_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    vst %v0, 160(%r15), 3 # 16-byte Folded Spill
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    brasl %r14, cos@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -2789,10 +2784,9 @@ define void @constrained_vector_exp_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    vst %v0, 160(%r15), 3 # 16-byte Folded Spill
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    brasl %r14, exp@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -3106,10 +3100,9 @@ define void @constrained_vector_exp2_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    vst %v0, 160(%r15), 3 # 16-byte Folded Spill
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    brasl %r14, exp2@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -3423,10 +3416,9 @@ define void @constrained_vector_log_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    vst %v0, 160(%r15), 3 # 16-byte Folded Spill
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    brasl %r14, log@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -3740,10 +3732,9 @@ define void @constrained_vector_log10_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    vst %v0, 160(%r15), 3 # 16-byte Folded Spill
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    brasl %r14, log10@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -4057,10 +4048,9 @@ define void @constrained_vector_log2_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    vst %v0, 160(%r15), 3 # 16-byte Folded Spill
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    brasl %r14, log2@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -4788,10 +4778,9 @@ define void @constrained_vector_log10_maxnum_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    vst %v0, 160(%r15), 3 # 16-byte Folded Spill
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    brasl %r14, fmax@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -5165,11 +5154,10 @@ define void @constrained_vector_minnum_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    ldr %f2, %f9
 ; SZ13-NEXT:    brasl %r14, fmin@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 200(%r15) # 8-byte Reload
 ; SZ13-NEXT:    ld %f9, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 312(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -6612,10 +6600,9 @@ define void @constrained_vector_tan_v3f64(ptr %a) #0 {
 ; SZ13-NEXT:    vst %v0, 160(%r15), 3 # 16-byte Folded Spill
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    brasl %r14, tan@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 192(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 304(%r15)
 ; SZ13-NEXT:    br %r14
 entry:
@@ -6977,11 +6964,10 @@ define void @constrained_vector_atan2_v3f64(ptr %a, ptr %b) #0 {
 ; SZ13-NEXT:    ldr %f0, %f8
 ; SZ13-NEXT:    ldr %f2, %f9
 ; SZ13-NEXT:    brasl %r14, atan2@PLT
-; SZ13-NEXT:    std %f0, 16(%r13)
-; SZ13-NEXT:    vl %v0, 160(%r15), 3 # 16-byte Folded Reload
+; SZ13-NEXT:    mvc 0(16,%r13), 160(%r15) # 16-byte Folded Reload
 ; SZ13-NEXT:    ld %f8, 216(%r15) # 8-byte Reload
 ; SZ13-NEXT:    ld %f9, 208(%r15) # 8-byte Reload
-; SZ13-NEXT:    vst %v0, 0(%r13), 4
+; SZ13-NEXT:    std %f0, 16(%r13)
 ; SZ13-NEXT:    lmg %r13, %r15, 328(%r15)
 ; SZ13-NEXT:    br %r14
 entry: