[AArch64][SVE] Optimize ptrue predicate pattern with known sve regist…

…er width.

For vectors that are exactly equal to getMaxSVEVectorSizeInBits, just use
AArch64SVEPredPattern::all, which can enable the use of unpredicated ptrue when available.

TestPlan: check-llvm

Differential Revision: https://reviews.llvm.org/D108706

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -18026,9 +18026,16 @@ static SDValue getPredicateForFixedLengthVector(SelectionDAG &DAG, SDLoc &DL,
       getSVEPredPatternFromNumElements(VT.getVectorNumElements());
   assert(PgPattern && "Unexpected element count for SVE predicate");
 
-  // TODO: For vectors that are exactly getMaxSVEVectorSizeInBits big, we can
-  // use AArch64SVEPredPattern::all, which can enable the use of unpredicated
+  // For vectors that are exactly getMaxSVEVectorSizeInBits big, we can use
+  // AArch64SVEPredPattern::all, which can enable the use of unpredicated
   // variants of instructions when available.
+  const auto &Subtarget =
+      static_cast<const AArch64Subtarget &>(DAG.getSubtarget());
+  unsigned MinSVESize = Subtarget.getMinSVEVectorSizeInBits();
+  unsigned MaxSVESize = Subtarget.getMaxSVEVectorSizeInBits();
+  if (MaxSVESize && MinSVESize == MaxSVESize &&
+      MaxSVESize == VT.getSizeInBits())
+    PgPattern = AArch64SVEPredPattern::all;
 
   MVT MaskVT;
   switch (VT.getVectorElementType().getSimpleVT().SimpleTy) {

llvm/test/CodeGen/AArch64/insert-subvector-res-legalization.ll

@@ -226,18 +226,17 @@ define <vscale x 2 x i32> @vec_scalable_subvec_fixed_idx_nonzero_large_i32(<vsca
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    ptrue p1.s, vl8
 ; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0]
-; CHECK-NEXT:    ld1w { z1.s }, p1/z, [x1]
 ; CHECK-NEXT:    cntd x8
+; CHECK-NEXT:    ld1w { z1.s }, p1/z, [x1]
 ; CHECK-NEXT:    subs x8, x8, #8
 ; CHECK-NEXT:    csel x8, xzr, x8, lo
 ; CHECK-NEXT:    mov w9, #8
 ; CHECK-NEXT:    cmp x8, #8
-; CHECK-NEXT:    ptrue p1.d, vl8
 ; CHECK-NEXT:    csel x8, x8, x9, lo
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    uunpklo z0.d, z1.s
 ; CHECK-NEXT:    mov x9, sp
-; CHECK-NEXT:    st1d { z0.d }, p1, [x9, x8, lsl #3]
+; CHECK-NEXT:    st1d { z0.d }, p0, [x9, x8, lsl #3]
 ; CHECK-NEXT:    ld1d { z0.d }, p0/z, [sp]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload

llvm/test/CodeGen/AArch64/sve-extract-vector.ll

@@ -186,12 +186,11 @@ define <4 x i64> @extract_fixed_v4i64_nxv2i64(<vscale x 2 x i64> %vec) nounwind
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    mov w10, #4
 ; CHECK-NEXT:    cmp x9, #4
-; CHECK-NEXT:    ptrue p1.d, vl4
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    csel x9, x9, x10, lo
 ; CHECK-NEXT:    mov x10, sp
-; CHECK-NEXT:    ld1d { z0.d }, p1/z, [x10, x9, lsl #3]
-; CHECK-NEXT:    st1d { z0.d }, p1, [x8]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x10, x9, lsl #3]
+; CHECK-NEXT:    st1d { z0.d }, p0, [x8]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret

llvm/test/CodeGen/AArch64/sve-fixed-length-optimize-ptrue.ll

@@ -0,0 +1,117 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -aarch64-sve-vector-bits-min=512 -aarch64-sve-vector-bits-max=512  < %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+define void @add_v64i8(<64 x i8>* %a, <64 x i8>* %b) #0 {
+; CHECK-LABEL: add_v64i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.b
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0]
+; CHECK-NEXT:    ld1b { z1.b }, p0/z, [x1]
+; CHECK-NEXT:    add z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT:    st1b { z0.b }, p0, [x0]
+; CHECK-NEXT:    ret
+  %op1 = load <64 x i8>, <64 x i8>* %a
+  %op2 = load <64 x i8>, <64 x i8>* %b
+  %res = add <64 x i8> %op1, %op2
+  store <64 x i8> %res, <64 x i8>* %a
+  ret void
+}
+
+define void @add_v32i16(<32 x i16>* %a, <32 x i16>* %b, <32 x i16>* %c) #0 {
+; CHECK-LABEL: add_v32i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0]
+; CHECK-NEXT:    ld1h { z1.h }, p0/z, [x1]
+; CHECK-NEXT:    add z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT:    st1h { z0.h }, p0, [x0]
+; CHECK-NEXT:    ret
+  %op1 = load <32 x i16>, <32 x i16>* %a
+  %op2 = load <32 x i16>, <32 x i16>* %b
+  %res = add <32 x i16> %op1, %op2
+  store <32 x i16> %res, <32 x i16>* %a
+  ret void
+}
+
+define void @abs_v16i32(<16 x i32>* %a) #0 {
+; CHECK-LABEL: abs_v16i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0]
+; CHECK-NEXT:    abs z0.s, p0/m, z0.s
+; CHECK-NEXT:    st1w { z0.s }, p0, [x0]
+; CHECK-NEXT:    ret
+  %op1 = load <16 x i32>, <16 x i32>* %a
+  %res = call <16 x i32> @llvm.abs.v16i32(<16 x i32> %op1, i1 false)
+  store <16 x i32> %res, <16 x i32>* %a
+  ret void
+}
+
+define void @abs_v8i64(<8 x i64>* %a) #0 {
+; CHECK-LABEL: abs_v8i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0]
+; CHECK-NEXT:    abs z0.d, p0/m, z0.d
+; CHECK-NEXT:    st1d { z0.d }, p0, [x0]
+; CHECK-NEXT:    ret
+  %op1 = load <8 x i64>, <8 x i64>* %a
+  %res = call <8 x i64> @llvm.abs.v8i64(<8 x i64> %op1, i1 false)
+  store <8 x i64> %res, <8 x i64>* %a
+  ret void
+}
+
+define void @fadd_v32f16(<32 x half>* %a, <32 x half>* %b) #0 {
+; CHECK-LABEL: fadd_v32f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0]
+; CHECK-NEXT:    ld1h { z1.h }, p0/z, [x1]
+; CHECK-NEXT:    fadd z0.h, z0.h, z1.h
+; CHECK-NEXT:    st1h { z0.h }, p0, [x0]
+; CHECK-NEXT:    ret
+  %op1 = load <32 x half>, <32 x half>* %a
+  %op2 = load <32 x half>, <32 x half>* %b
+  %res = fadd <32 x half> %op1, %op2
+  store <32 x half> %res, <32 x half>* %a
+  ret void
+}
+
+define void @fadd_v16f32(<16 x float>* %a, <16 x float>* %b) #0 {
+; CHECK-LABEL: fadd_v16f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0]
+; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x1]
+; CHECK-NEXT:    fadd z0.s, z0.s, z1.s
+; CHECK-NEXT:    st1w { z0.s }, p0, [x0]
+; CHECK-NEXT:    ret
+  %op1 = load <16 x float>, <16 x float>* %a
+  %op2 = load <16 x float>, <16 x float>* %b
+  %res = fadd <16 x float> %op1, %op2
+  store <16 x float> %res, <16 x float>* %a
+  ret void
+}
+
+define void @fadd_v8f64(<8 x double>* %a, <8 x double>* %b) #0 {
+; CHECK-LABEL: fadd_v8f64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0]
+; CHECK-NEXT:    ld1d { z1.d }, p0/z, [x1]
+; CHECK-NEXT:    fadd z0.d, z0.d, z1.d
+; CHECK-NEXT:    st1d { z0.d }, p0, [x0]
+; CHECK-NEXT:    ret
+  %op1 = load <8 x double>, <8 x double>* %a
+  %op2 = load <8 x double>, <8 x double>* %b
+  %res = fadd <8 x double> %op1, %op2
+  store <8 x double> %res, <8 x double>* %a
+  ret void
+}
+
+declare <16 x i32> @llvm.abs.v16i32(<16 x i32>, i1)
+declare <8 x i64> @llvm.abs.v8i64(<8 x i64>, i1)
+
+attributes #0 = { "target-features"="+sve" }

llvm/test/CodeGen/AArch64/sve-insert-vector.ll

@@ -329,19 +329,18 @@ define <vscale x 2 x i64> @insert_fixed_v4i64_nxv2i64(<vscale x 2 x i64> %vec, <
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    ptrue p0.d, vl4
+; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    cntd x8
 ; CHECK-NEXT:    ld1d { z1.d }, p0/z, [x0]
 ; CHECK-NEXT:    subs x8, x8, #4
 ; CHECK-NEXT:    csel x8, xzr, x8, lo
 ; CHECK-NEXT:    mov w9, #4
 ; CHECK-NEXT:    cmp x8, #4
-; CHECK-NEXT:    ptrue p1.d
 ; CHECK-NEXT:    csel x8, x8, x9, lo
 ; CHECK-NEXT:    mov x9, sp
-; CHECK-NEXT:    st1d { z0.d }, p1, [sp]
+; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    st1d { z1.d }, p0, [x9, x8, lsl #3]
-; CHECK-NEXT:    ld1d { z0.d }, p1/z, [sp]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [sp]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret

llvm/test/CodeGen/AArch64/sve-vscale-attr.ll

@@ -63,7 +63,7 @@ define void @func_vscale2_2(<16 x i32>* %a, <16 x i32>* %b) #2 {
 ; CHECK-LABEL: func_vscale2_2:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    mov x8, #8
-; CHECK-NEXT:    ptrue p0.s, vl8
+; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, x8, lsl #2]
 ; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x0]
 ; CHECK-NEXT:    ld1w { z2.s }, p0/z, [x1, x8, lsl #2]
@@ -108,7 +108,7 @@ attributes #3 = { "target-features"="+sve" vscale_range(2,4) }
 define void @func_vscale4_4(<16 x i32>* %a, <16 x i32>* %b) #4 {
 ; CHECK-LABEL: func_vscale4_4:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ptrue p0.s, vl16
+; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0]
 ; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x1]
 ; CHECK-NEXT:    add z0.s, p0/m, z0.s, z1.s