[llvm] [RISCV][CostModel] VPIntrinsics have same cost as their non-vp counterparts (PR #67178)

Michael Maitland via llvm-commits llvm-commits at lists.llvm.org
Fri Sep 22 14:22:45 PDT 2023


https://github.com/michaelmaitland updated https://github.com/llvm/llvm-project/pull/67178

>From 08c1a2997e90218cfec5106b38bd029ccec61e59 Mon Sep 17 00:00:00 2001
From: Michael Maitland <michaeltmaitland at gmail.com>
Date: Fri, 22 Sep 2023 11:26:28 -0700
Subject: [PATCH 1/3] [RISCV][CostModel] Precommit RISCV cost model tests for
 VPIntrinsics

On RISCV, only a few VPIntrinsics have their cost modeled by the
VectorIntrinsicCostTable. Even so, none of those entries consider LMUL.
All other VPIntrinsics do not have meaningful modeling.
---
 .../CostModel/RISCV/rvv-intrinsics.ll         | 193 ++++++++++++++++++
 1 file changed, 193 insertions(+)

diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
index 6dcc218981f7a7a..1a3780599a80181 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
@@ -206,6 +206,199 @@ define void @vp_fshl() {
   ret void
 }
 
+define void @add() {
+; CHECK-LABEL: 'add'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %t0 = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t1 = add <2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %t2 = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t3 = add <4 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %t4 = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t5 = add <8 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %t6 = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t7 = add <16 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %t8 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = add <2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %t10 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t12 = add <4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %t13 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t14 = add <8 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %t15 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t16 = add <16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t17 = call <vscale x 2 x i8> @llvm.vp.add.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = add <vscale x 2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t19 = call <vscale x 4 x i8> @llvm.vp.add.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t20 = add <vscale x 4 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t21 = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t22 = add <vscale x 8 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t23 = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t24 = add <vscale x 16 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t25 = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = add <vscale x 2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t27 = call <vscale x 4 x i64> @llvm.vp.add.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = add <vscale x 4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t29 = call <vscale x 8 x i64> @llvm.vp.add.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = add <vscale x 8 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t31 = call <vscale x 16 x i64> @llvm.vp.add.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t32 = add <vscale x 16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  %t0 = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+  %t1 = add <2 x i8> undef, undef
+  %t2 = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+  %t3 = add <4 x i8> undef, undef
+  %t4 = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+  %t5 = add <8 x i8> undef, undef
+  %t6 = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+  %t7 = add <16 x i8> undef, undef
+  %t8 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+  %t9 = add <2 x i64> undef, undef
+  %t10 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+  %t12 = add <4 x i64> undef, undef
+  %t13 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+  %t14 = add <8 x i64> undef, undef
+  %t15 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+  %t16 = add <16 x i64> undef, undef
+  %t17 = call <vscale x 2 x i8> @llvm.vp.add.nv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t18 = add <vscale x 2 x i8> undef, undef
+  %t19 = call <vscale x 4 x i8> @llvm.vp.add.nv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t20 = add <vscale x 4 x i8> undef, undef
+  %t21 = call <vscale x 8 x i8> @llvm.vp.add.nv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t22 = add <vscale x 8 x i8> undef, undef
+  %t23 = call <vscale x 16 x i8> @llvm.vp.add.nv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t24 = add <vscale x 16 x i8> undef, undef
+  %t25 = call <vscale x 2 x i64> @llvm.vp.add.nv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t26 = add <vscale x 2 x i64> undef, undef
+  %t27 = call <vscale x 4 x i64> @llvm.vp.add.nv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t28 = add <vscale x 4 x i64> undef, undef
+  %t29 = call <vscale x 8 x i64> @llvm.vp.add.nv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t30 = add <vscale x 8 x i64> undef, undef
+  %t31 = call <vscale x 16 x i64> @llvm.vp.add.nv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t32 = add <vscale x 16 x i64> undef, undef
+  ret void
+}
+
+define void @abs() {
+; CHECK-LABEL: 'abs'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %1 = call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %3 = call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %5 = call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %6 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %7 = call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 2 x i8> @llvm.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %20 = call <vscale x 4 x i8> @llvm.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <vscale x 8 x i8> @llvm.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %30 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %32 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 0, <2 x i1> undef, i32 undef)
+  call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 0)
+  call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 0, <4 x i1> undef, i32 undef)
+  call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 0)
+  call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 0, <8 x i1> undef, i32 undef)
+  call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 0)
+  call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 0, <16 x i1> undef, i32 undef)
+  call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 0)
+  call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 0, <2 x i1> undef, i32 undef)
+  call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 0)
+  call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 0, <4 x i1> undef, i32 undef)
+  call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 0)
+  call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 0, <8 x i1> undef, i32 undef)
+  call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 0)
+  call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 0, <16 x i1> undef, i32 undef)
+  call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 0)
+  call <vscale x 2 x i8> @llvm.vp.abs.nv2i8(<vscale x 2 x i8> undef, i1 0, <vscale x 2 x i1> undef, i32 undef)
+  call <vscale x 2 x i8> @llvm.abs.nv2i8(<vscale x 2 x i8> undef, i1 0)
+  call <vscale x 4 x i8> @llvm.vp.abs.nv4i8(<vscale x 4 x i8> undef, i1 0, <vscale x 4 x i1> undef, i32 undef)
+  call <vscale x 4 x i8> @llvm.abs.nv4i8(<vscale x 4 x i8> undef, i1 0)
+  call <vscale x 8 x i8> @llvm.vp.abs.nv8i8(<vscale x 8 x i8> undef, i1 0, <vscale x 8 x i1> undef, i32 undef)
+  call <vscale x 8 x i8> @llvm.abs.nv8i8(<vscale x 8 x i8> undef, i1 0)
+  call <vscale x 16 x i8> @llvm.vp.abs.nv16i8(<vscale x 16 x i8> undef, i1 0, <vscale x 16 x i1> undef, i32 undef)
+  call <vscale x 16 x i8> @llvm.abs.nv16i8(<vscale x 16 x i8> undef, i1 0)
+  call <vscale x 2 x i64> @llvm.vp.abs.nv2i64(<vscale x 2 x i64> undef, i1 0, <vscale x 2 x i1> undef, i32 undef)
+  call <vscale x 2 x i64> @llvm.abs.nv2i64(<vscale x 2 x i64> undef, i1 0)
+  call <vscale x 4 x i64> @llvm.vp.abs.nv4i64(<vscale x 4 x i64> undef, i1 0, <vscale x 4 x i1> undef, i32 undef)
+  call <vscale x 4 x i64> @llvm.abs.nv4i64(<vscale x 4 x i64> undef, i1 0)
+  call <vscale x 8 x i64> @llvm.vp.abs.nv8i64(<vscale x 8 x i64> undef, i1 0, <vscale x 8 x i1> undef, i32 undef)
+  call <vscale x 8 x i64> @llvm.abs.nv8i64(<vscale x 8 x i64> undef, i1 0)
+  call <vscale x 16 x i64> @llvm.vp.abs.nv16i64(<vscale x 16 x i64> undef, i1 0, <vscale x 16 x i1> undef, i32 undef)
+  call <vscale x 16 x i64> @llvm.abs.nv16i64(<vscale x 16 x i64> undef, i1 0)
+  ret void
+}
+
+declare <2 x i8> @llvm.vp.add.v2i8(<2 x i8>, <2 x i8>, <2 x i1>, i32)
+declare <4 x i8> @llvm.vp.add.v4i8(<4 x i8>, <4 x i8>, <4 x i1>, i32)
+declare <8 x i8> @llvm.vp.add.v8i8(<8 x i8>, <8 x i8>, <8 x i1>, i32)
+declare <16 x i8> @llvm.vp.add.v16i8(<16 x i8>, <16 x i8>, <16 x i1>, i32)
+declare <2 x i64> @llvm.vp.add.v2i64(<2 x i64>, <2 x i64>, <2 x i1>, i32)
+declare <4 x i64> @llvm.vp.add.v4i64(<4 x i64>, <4 x i64>, <4 x i1>, i32)
+declare <8 x i64> @llvm.vp.add.v8i64(<8 x i64>, <8 x i64>, <8 x i1>, i32)
+declare <16 x i64> @llvm.vp.add.v16i64(<16 x i64>, <16 x i64>, <16 x i1>, i32)
+declare <vscale x 2 x i8> @llvm.vp.add.nv2i8(<vscale x 2 x i8>, <vscale x 2 x i8>, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i8> @llvm.vp.add.nv4i8(<vscale x 4 x i8>, <vscale x 4 x i8>, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i8> @llvm.vp.add.nv8i8(<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i8> @llvm.vp.add.nv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i1>, i32)
+declare <vscale x 2 x i64> @llvm.vp.add.nv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i64> @llvm.vp.add.nv4i64(<vscale x 4 x i64>, <vscale x 4 x i64>, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i64> @llvm.vp.add.nv8i64(<vscale x 8 x i64>, <vscale x 8 x i64>, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i64> @llvm.vp.add.nv16i64(<vscale x 16 x i64>, <vscale x 16 x i64>, <vscale x 16 x i1>, i32)
+
+declare <2 x i8> @llvm.vp.abs.v2i8(<2 x i8>, i1, <2 x i1>, i32)
+declare <4 x i8> @llvm.vp.abs.v4i8(<4 x i8>, i1, <4 x i1>, i32)
+declare <8 x i8> @llvm.vp.abs.v8i8(<8 x i8>, i1, <8 x i1>, i32)
+declare <16 x i8> @llvm.vp.abs.v16i8(<16 x i8>, i1, <16 x i1>, i32)
+declare <2 x i64> @llvm.vp.abs.v2i64(<2 x i64>, i1, <2 x i1>, i32)
+declare <4 x i64> @llvm.vp.abs.v4i64(<4 x i64>, i1, <4 x i1>, i32)
+declare <8 x i64> @llvm.vp.abs.v8i64(<8 x i64>, i1, <8 x i1>, i32)
+declare <16 x i64> @llvm.vp.abs.v16i64(<16 x i64>, i1, <16 x i1>, i32)
+declare <vscale x 2 x i8> @llvm.vp.abs.nv2i8(<vscale x 2 x i8>, i1, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i8> @llvm.vp.abs.nv4i8(<vscale x 4 x i8>, i1, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i8> @llvm.vp.abs.nv8i8(<vscale x 8 x i8>, i1, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i8> @llvm.vp.abs.nv16i8(<vscale x 16 x i8>, i1, <vscale x 16 x i1>, i32)
+declare <vscale x 2 x i64> @llvm.vp.abs.nv2i64(<vscale x 2 x i64>, i1, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i64> @llvm.vp.abs.nv4i64(<vscale x 4 x i64>, i1, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i64> @llvm.vp.abs.nv8i64(<vscale x 8 x i64>, i1, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i64> @llvm.vp.abs.nv16i64(<vscale x 16 x i64>, i1, <vscale x 16 x i1>, i32)
+
+declare <2 x i8> @llvm.abs.v2i8(<2 x i8>, i1)
+declare <4 x i8> @llvm.abs.v4i8(<4 x i8>, i1)
+declare <8 x i8> @llvm.abs.v8i8(<8 x i8>, i1)
+declare <16 x i8> @llvm.abs.v16i8(<16 x i8>, i1)
+declare <2 x i64> @llvm.abs.v2i64(<2 x i64>, i1)
+declare <4 x i64> @llvm.abs.v4i64(<4 x i64>, i1)
+declare <8 x i64> @llvm.abs.v8i64(<8 x i64>, i1)
+declare <16 x i64> @llvm.abs.v16i64(<16 x i64>, i1)
+declare <vscale x 2 x i8> @llvm.abs.nv2i8(<vscale x 2 x i8>, i1)
+declare <vscale x 4 x i8> @llvm.abs.nv4i8(<vscale x 4 x i8>, i1)
+declare <vscale x 8 x i8> @llvm.abs.nv8i8(<vscale x 8 x i8>, i1)
+declare <vscale x 16 x i8> @llvm.abs.nv16i8(<vscale x 16 x i8>, i1)
+declare <vscale x 2 x i64> @llvm.abs.nv2i64(<vscale x 2 x i64>, i1)
+declare <vscale x 4 x i64> @llvm.abs.nv4i64(<vscale x 4 x i64>, i1)
+declare <vscale x 8 x i64> @llvm.abs.nv8i64(<vscale x 8 x i64>, i1)
+declare <vscale x 16 x i64> @llvm.abs.nv16i64(<vscale x 16 x i64>, i1)
+
 declare <vscale x 1 x i32> @llvm.fshr.nxv4i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
 declare <vscale x 1 x i32> @llvm.fshl.nxv4i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
 

>From 38df517e4f6b2c9b49602d603be82d63c8e48228 Mon Sep 17 00:00:00 2001
From: Michael Maitland <michaeltmaitland at gmail.com>
Date: Fri, 22 Sep 2023 11:30:23 -0700
Subject: [PATCH 2/3] [RISCV][CostModel] VPIntrinsics have same cost as their
 non-vp counterparts

On RISCV, only a few VPIntrinsics have their cost modeled by the
VectorIntrinsicCostTable. Even so, none of those entries consider LMUL.
All other VPIntrinsics do not have meaningful modeling.

This patch models the cost of a VPIntrinsic as the cost of its non-VP
counterpart. It is possible that the VP Intrinsic is cheaper than the non-VP
version depending on VL. On RISCV, this may be due two reasons (if the
instruction is part of a loop):
  1. A smaller VL can be used on the last iteration of the loop.
  2. The VP instruction may avoid a scalar remainder loop.

I have left this as a TODO since I think this change puts us on the right path
of modeling the cost of a VPInstruction, and it isn't entierly clear to me how
much of a discount we should give to a known VL<VLMAX or what to do when VL
is unknown at compile time.
---
 llvm/include/llvm/CodeGen/BasicTTIImpl.h      | 27 ++++++++
 llvm/test/Analysis/CostModel/RISCV/gep.ll     |  8 +--
 .../CostModel/RISCV/rvv-intrinsics.ll         | 64 +++++++++----------
 3 files changed, 63 insertions(+), 36 deletions(-)

diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index c11d558a73e9d09..2160025c8108bdd 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -1687,6 +1687,33 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
     }
     }
 
+    // VP Intrinsics should have the same cost as their non-vp counterpart.
+    // TODO: Adjust the cost to make the vp intrinsic cheaper than its non-vp
+    // counterpart when the vector length argument is smaller than the maximum
+    // vector length.
+    if (VPIntrinsic::isVPIntrinsic(ICA.getID())) {
+      std::optional<Intrinsic::ID> FOp =
+          VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
+      if (FOp)
+        return thisT()->getArithmeticInstrCost(*FOp, ICA.getReturnType(),
+                                               CostKind);
+
+      std::optional<Intrinsic::ID> FID =
+          VPIntrinsic::getFunctionalIntrinsicIDForVP(ICA.getID());
+      if (FID) {
+        // Non-vp version will have same Args/Tys except mask and vector length.
+        ArrayRef<const Value *> NewArgs(ICA.getArgs().begin(),
+                                        ICA.getArgs().end() - 2);
+        ArrayRef<Type *> NewTys(ICA.getArgTypes().begin(),
+                                ICA.getArgTypes().end() - 2);
+
+        IntrinsicCostAttributes NewICA(*FID, ICA.getReturnType(), NewArgs,
+                                       NewTys, ICA.getFlags(), ICA.getInst(),
+                                       ICA.getScalarizationCost());
+        return thisT()->getIntrinsicInstrCost(NewICA, CostKind);
+      }
+    }
+
     // Assume that we need to scalarize this intrinsic.
     // Compute the scalarization overhead based on Args for a vector
     // intrinsic.
diff --git a/llvm/test/Analysis/CostModel/RISCV/gep.ll b/llvm/test/Analysis/CostModel/RISCV/gep.ll
index c7a3e5d30aba7f4..2c309412b9b2e35 100644
--- a/llvm/test/Analysis/CostModel/RISCV/gep.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/gep.ll
@@ -270,7 +270,7 @@ define void @non_foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x4 = call <2 x i8> @llvm.masked.expandload.v2i8(ptr %4, <2 x i1> undef, <2 x i8> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = getelementptr i8, ptr %base, i32 42
-; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = getelementptr i8, ptr %base, i32 42
@@ -282,7 +282,7 @@ define void @non_foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v2i8(<2 x i8> undef, ptr %10, <2 x i1> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = getelementptr i8, ptr %base, i32 42
-; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> undef, ptr %12, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
@@ -340,7 +340,7 @@ define void @foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %4 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x4 = call <2 x i8> @llvm.masked.expandload.v2i8(ptr %4, <2 x i1> undef, <2 x i8> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %5 = getelementptr i8, ptr %base, i32 0
-; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %6 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %7 = getelementptr i8, ptr %base, i32 0
@@ -352,7 +352,7 @@ define void @foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %10 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v2i8(<2 x i8> undef, ptr %10, <2 x i1> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %11 = getelementptr i8, ptr %base, i32 0
-; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %12 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> undef, ptr %12, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
index 1a3780599a80181..6ad1e31ff61f63a 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
@@ -208,37 +208,37 @@ define void @vp_fshl() {
 
 define void @add() {
 ; CHECK-LABEL: 'add'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %t0 = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t1 = add <2 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %t2 = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t3 = add <4 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %t4 = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t5 = add <8 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %t6 = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t7 = add <16 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %t8 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = add <2 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %t10 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t10 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t12 = add <4 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %t13 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t13 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t14 = add <8 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %t15 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t15 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t16 = add <16 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t17 = call <vscale x 2 x i8> @llvm.vp.add.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t17 = call <vscale x 2 x i8> @llvm.vp.add.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = add <vscale x 2 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t19 = call <vscale x 4 x i8> @llvm.vp.add.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t19 = call <vscale x 4 x i8> @llvm.vp.add.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t20 = add <vscale x 4 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t21 = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t21 = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t22 = add <vscale x 8 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t23 = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t23 = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t24 = add <vscale x 16 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t25 = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t25 = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = add <vscale x 2 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t27 = call <vscale x 4 x i64> @llvm.vp.add.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t27 = call <vscale x 4 x i64> @llvm.vp.add.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = add <vscale x 4 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t29 = call <vscale x 8 x i64> @llvm.vp.add.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t29 = call <vscale x 8 x i64> @llvm.vp.add.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = add <vscale x 8 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t31 = call <vscale x 16 x i64> @llvm.vp.add.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t31 = call <vscale x 16 x i64> @llvm.vp.add.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t32 = add <vscale x 16 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
@@ -279,37 +279,37 @@ define void @add() {
 
 define void @abs() {
 ; CHECK-LABEL: 'abs'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %1 = call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %3 = call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %5 = call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %6 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %7 = call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %7 = call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 2 x i8> @llvm.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %20 = call <vscale x 4 x i8> @llvm.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <vscale x 8 x i8> @llvm.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %30 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %32 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;

>From 6e16ac1ddd9fc040c5c809af5a24de5e0aa7abdd Mon Sep 17 00:00:00 2001
From: Michael Maitland <michaeltmaitland at gmail.com>
Date: Fri, 22 Sep 2023 14:15:34 -0700
Subject: [PATCH 3/3] Load/Store instructions should use getMemoryOpCost

---
 llvm/include/llvm/CodeGen/BasicTTIImpl.h      |  33 +++-
 llvm/test/Analysis/CostModel/RISCV/gep.ll     |   4 +-
 .../CostModel/RISCV/rvv-intrinsics.ll         | 176 ++++++++++++++++++
 3 files changed, 209 insertions(+), 4 deletions(-)

diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index 2160025c8108bdd..e1a84144efb711a 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -1692,11 +1692,40 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
     // counterpart when the vector length argument is smaller than the maximum
     // vector length.
     if (VPIntrinsic::isVPIntrinsic(ICA.getID())) {
-      std::optional<Intrinsic::ID> FOp =
+      std::optional<unsigned> FOp =
           VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
-      if (FOp)
+      if (FOp) {
+        if (ICA.getID() == Intrinsic::vp_load) {
+          Align Alignment = isa_and_nonnull<VPIntrinsic>(ICA.getInst())
+                                ? cast<VPIntrinsic>(ICA.getInst())
+                                      ->getPointerAlignment()
+                                      .valueOrOne()
+                                : Align(1);
+          unsigned AS = ICA.getArgs().size() >= 1 &&
+                                isa<PointerType>(ICA.getArgs()[0]->getType())
+                            ? cast<PointerType>(ICA.getArgs()[0]->getType())
+                                  ->getAddressSpace()
+                            : 0;
+          return thisT()->getMemoryOpCost(*FOp, ICA.getReturnType(), Alignment,
+                                          AS, CostKind);
+        } else if (ICA.getID() == Intrinsic::vp_store) {
+          Align Alignment = isa_and_nonnull<VPIntrinsic>(ICA.getInst())
+                                ? cast<VPIntrinsic>(ICA.getInst())
+                                      ->getPointerAlignment()
+                                      .valueOrOne()
+                                : Align(1);
+          unsigned AS = ICA.getArgs().size() >= 2 &&
+                                isa<PointerType>(ICA.getArgs()[1]->getType())
+                            ? cast<PointerType>(ICA.getArgs()[1]->getType())
+                                  ->getAddressSpace()
+                            : 0;
+          return thisT()->getMemoryOpCost(*FOp, Args[0]->getType(), Alignment,
+                                          AS, CostKind);
+        }
+        // TODO: Support other kinds of Intrinsics (i.e. reductions)
         return thisT()->getArithmeticInstrCost(*FOp, ICA.getReturnType(),
                                                CostKind);
+      }
 
       std::optional<Intrinsic::ID> FID =
           VPIntrinsic::getFunctionalIntrinsicIDForVP(ICA.getID());
diff --git a/llvm/test/Analysis/CostModel/RISCV/gep.ll b/llvm/test/Analysis/CostModel/RISCV/gep.ll
index 2c309412b9b2e35..a999ede4568acb6 100644
--- a/llvm/test/Analysis/CostModel/RISCV/gep.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/gep.ll
@@ -270,7 +270,7 @@ define void @non_foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x4 = call <2 x i8> @llvm.masked.expandload.v2i8(ptr %4, <2 x i1> undef, <2 x i8> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = getelementptr i8, ptr %base, i32 42
-; RVI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = getelementptr i8, ptr %base, i32 42
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = getelementptr i8, ptr %base, i32 42
@@ -340,7 +340,7 @@ define void @foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %4 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x4 = call <2 x i8> @llvm.masked.expandload.v2i8(ptr %4, <2 x i1> undef, <2 x i8> undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %5 = getelementptr i8, ptr %base, i32 0
-; RVI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
+; RVI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %6 = getelementptr i8, ptr %base, i32 0
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
 ; RVI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %7 = getelementptr i8, ptr %base, i32 0
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
index 6ad1e31ff61f63a..8d208a835fe2077 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
@@ -348,6 +348,148 @@ define void @abs() {
   ret void
 }
 
+define void @load() {
+; CHECK-LABEL: 'load'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t1 = load <2 x i8>, ptr undef, align 2
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.load.v4i8.p0(ptr undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t3 = load <4 x i8>, ptr undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.load.v8i8.p0(ptr undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t5 = load <8 x i8>, ptr undef, align 8
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.load.v16i8.p0(ptr undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t7 = load <16 x i8>, ptr undef, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i64> @llvm.vp.load.v2i64.p0(ptr undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = load <2 x i64>, ptr undef, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t10 = call <4 x i64> @llvm.vp.load.v4i64.p0(ptr undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t12 = load <4 x i64>, ptr undef, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t13 = call <8 x i64> @llvm.vp.load.v8i64.p0(ptr undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t14 = load <8 x i64>, ptr undef, align 64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t15 = call <16 x i64> @llvm.vp.load.v16i64.p0(ptr undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t16 = load <16 x i64>, ptr undef, align 128
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t17 = call <vscale x 2 x i8> @llvm.vp.load.nxv2i8.p0(ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = load <vscale x 2 x i8>, ptr undef, align 2
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t19 = call <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0(ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t20 = load <vscale x 4 x i8>, ptr undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t21 = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0(ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t22 = load <vscale x 8 x i8>, ptr undef, align 8
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t23 = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t24 = load <vscale x 16 x i8>, ptr undef, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t25 = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = load <vscale x 2 x i64>, ptr undef, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t27 = call <vscale x 4 x i64> @llvm.vp.load.nxv4i64.p0(ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = load <vscale x 4 x i64>, ptr undef, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t29 = call <vscale x 8 x i64> @llvm.vp.load.nxv8i64.p0(ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = load <vscale x 8 x i64>, ptr undef, align 64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t31 = call <vscale x 16 x i64> @llvm.vp.load.nxv16i64.p0(ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t32 = load <vscale x 16 x i64>, ptr undef, align 128
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  %t0 = call <2 x i8> @llvm.vp.load.v2i8(ptr undef, <2 x i1> undef, i32 undef)
+  %t1 = load <2 x i8>, ptr undef
+  %t2 = call <4 x i8> @llvm.vp.load.v4i8(ptr undef, <4 x i1> undef, i32 undef)
+  %t3 = load <4 x i8>, ptr undef
+  %t4 = call <8 x i8> @llvm.vp.load.v8i8(ptr undef, <8 x i1> undef, i32 undef)
+  %t5 = load <8 x i8>, ptr undef
+  %t6 = call <16 x i8> @llvm.vp.load.v16i8(ptr undef, <16 x i1> undef, i32 undef)
+  %t7 = load <16 x i8>, ptr undef
+  %t8 = call <2 x i64> @llvm.vp.load.v2i64(ptr undef, <2 x i1> undef, i32 undef)
+  %t9 = load <2 x i64>, ptr undef
+  %t10 = call <4 x i64> @llvm.vp.load.v4i64(ptr undef, <4 x i1> undef, i32 undef)
+  %t12 = load <4 x i64>, ptr undef
+  %t13 = call <8 x i64> @llvm.vp.load.v8i64(ptr undef, <8 x i1> undef, i32 undef)
+  %t14 = load <8 x i64>, ptr undef
+  %t15 = call <16 x i64> @llvm.vp.load.v16i64(ptr undef, <16 x i1> undef, i32 undef)
+  %t16 = load <16 x i64>, ptr undef
+  %t17 = call <vscale x 2 x i8> @llvm.vp.load.nv2i8(ptr undef, <vscale x 2 x i1> undef, i32 undef)
+  %t18 = load <vscale x 2 x i8>, ptr undef
+  %t19 = call <vscale x 4 x i8> @llvm.vp.load.nv4i8(ptr undef, <vscale x 4 x i1> undef, i32 undef)
+  %t20 = load <vscale x 4 x i8>, ptr undef
+  %t21 = call <vscale x 8 x i8> @llvm.vp.load.nv8i8(ptr undef, <vscale x 8 x i1> undef, i32 undef)
+  %t22 = load <vscale x 8 x i8>, ptr undef
+  %t23 = call <vscale x 16 x i8> @llvm.vp.load.nv16i8(ptr undef, <vscale x 16 x i1> undef, i32 undef)
+  %t24 = load <vscale x 16 x i8>, ptr undef
+  %t25 = call <vscale x 2 x i64> @llvm.vp.load.nv2i64(ptr undef, <vscale x 2 x i1> undef, i32 undef)
+  %t26 = load <vscale x 2 x i64>, ptr undef
+  %t27 = call <vscale x 4 x i64> @llvm.vp.load.nv4i64(ptr undef, <vscale x 4 x i1> undef, i32 undef)
+  %t28 = load <vscale x 4 x i64>, ptr undef
+  %t29 = call <vscale x 8 x i64> @llvm.vp.load.nv8i64(ptr undef, <vscale x 8 x i1> undef, i32 undef)
+  %t30 = load <vscale x 8 x i64>, ptr undef
+  %t31 = call <vscale x 16 x i64> @llvm.vp.load.nv16i64(ptr undef, <vscale x 16 x i1> undef, i32 undef)
+  %t32 = load <vscale x 16 x i64>, ptr undef
+  ret void
+}
+
+define void @store() {
+; CHECK-LABEL: 'store'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i8> undef, ptr undef, align 2
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v4i8.p0(<4 x i8> undef, ptr undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i8> undef, ptr undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v8i8.p0(<8 x i8> undef, ptr undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <8 x i8> undef, ptr undef, align 8
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v16i8.p0(<16 x i8> undef, ptr undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <16 x i8> undef, ptr undef, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i64.p0(<2 x i64> undef, ptr undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i64> undef, ptr undef, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.vp.store.v4i64.p0(<4 x i64> undef, ptr undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i64> undef, ptr undef, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.vp.store.v8i64.p0(<8 x i64> undef, ptr undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x i64> undef, ptr undef, align 64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.vp.store.v16i64.p0(<16 x i64> undef, ptr undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <16 x i64> undef, ptr undef, align 128
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.nxv2i8.p0(<vscale x 2 x i8> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i8> undef, ptr undef, align 2
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.nxv4i8.p0(<vscale x 4 x i8> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i8> undef, ptr undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.nxv8i8.p0(<vscale x 8 x i8> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i8> undef, ptr undef, align 8
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 16 x i8> undef, ptr undef, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 2 x i64> undef, ptr undef, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.vp.store.nxv4i64.p0(<vscale x 4 x i64> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 4 x i64> undef, ptr undef, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.vp.store.nxv8i64.p0(<vscale x 8 x i64> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <vscale x 8 x i64> undef, ptr undef, align 64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.vp.store.nxv16i64.p0(<vscale x 16 x i64> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <vscale x 16 x i64> undef, ptr undef, align 128
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  call void @llvm.vp.store.v2i8(<2 x i8> undef, ptr undef, <2 x i1> undef, i32 undef)
+  store <2 x i8> undef, ptr undef
+  call void @llvm.vp.store.v4i8(<4 x i8> undef, ptr undef, <4 x i1> undef, i32 undef)
+  store <4 x i8> undef, ptr undef
+  call void @llvm.vp.store.v8i8(<8 x i8> undef, ptr undef, <8 x i1> undef, i32 undef)
+  store <8 x i8> undef, ptr undef
+  call void @llvm.vp.store.v16i8(<16 x i8> undef, ptr undef, <16 x i1> undef, i32 undef)
+  store <16 x i8> undef, ptr undef
+  call void @llvm.vp.store.v2i64(<2 x i64> undef, ptr undef, <2 x i1> undef, i32 undef)
+  store <2 x i64> undef, ptr undef
+  call void @llvm.vp.store.v4i64(<4 x i64> undef, ptr undef, <4 x i1> undef, i32 undef)
+  store <4 x i64> undef, ptr undef
+  call void @llvm.vp.store.v8i64(<8 x i64> undef, ptr undef, <8 x i1> undef, i32 undef)
+  store <8 x i64> undef, ptr undef
+  call void @llvm.vp.store.v16i64(<16 x i64> undef, ptr undef, <16 x i1> undef, i32 undef)
+  store <16 x i64> undef, ptr undef
+  call void @llvm.vp.store.nv2i8(<vscale x 2 x i8> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
+  store <vscale x 2 x i8> undef, ptr undef
+  call void @llvm.vp.store.nv4i8(<vscale x 4 x i8> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
+  store <vscale x 4 x i8> undef, ptr undef
+  call void @llvm.vp.store.nv8i8(<vscale x 8 x i8> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
+  store <vscale x 8 x i8> undef, ptr undef
+  call void @llvm.vp.store.nv16i8(<vscale x 16 x i8> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
+  store <vscale x 16 x i8> undef, ptr undef
+  call void @llvm.vp.store.nv2i64(<vscale x 2 x i64> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
+  store <vscale x 2 x i64> undef, ptr undef
+  call void @llvm.vp.store.nv4i64(<vscale x 4 x i64> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
+  store <vscale x 4 x i64> undef, ptr undef
+  call void @llvm.vp.store.nv8i64(<vscale x 8 x i64> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
+  store <vscale x 8 x i64> undef, ptr undef
+  call void @llvm.vp.store.nv16i64(<vscale x 16 x i64> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
+  store <vscale x 16 x i64> undef, ptr undef
+  ret void
+}
+
 declare <2 x i8> @llvm.vp.add.v2i8(<2 x i8>, <2 x i8>, <2 x i1>, i32)
 declare <4 x i8> @llvm.vp.add.v4i8(<4 x i8>, <4 x i8>, <4 x i1>, i32)
 declare <8 x i8> @llvm.vp.add.v8i8(<8 x i8>, <8 x i8>, <8 x i1>, i32)
@@ -399,6 +541,40 @@ declare <vscale x 4 x i64> @llvm.abs.nv4i64(<vscale x 4 x i64>, i1)
 declare <vscale x 8 x i64> @llvm.abs.nv8i64(<vscale x 8 x i64>, i1)
 declare <vscale x 16 x i64> @llvm.abs.nv16i64(<vscale x 16 x i64>, i1)
 
+declare <2 x i8> @llvm.vp.load.v2i8(ptr, <2 x i1>, i32)
+declare <4 x i8> @llvm.vp.load.v4i8(ptr, <4 x i1>, i32)
+declare <8 x i8> @llvm.vp.load.v8i8(ptr, <8 x i1>, i32)
+declare <16 x i8> @llvm.vp.load.v16i8(ptr, <16 x i1>, i32)
+declare <2 x i64> @llvm.vp.load.v2i64(ptr, <2 x i1>, i32)
+declare <4 x i64> @llvm.vp.load.v4i64(ptr, <4 x i1>, i32)
+declare <8 x i64> @llvm.vp.load.v8i64(ptr, <8 x i1>, i32)
+declare <16 x i64> @llvm.vp.load.v16i64(ptr, <16 x i1>, i32)
+declare <vscale x 2 x i8> @llvm.vp.load.nv2i8(ptr, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i8> @llvm.vp.load.nv4i8(ptr, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i8> @llvm.vp.load.nv8i8(ptr, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i8> @llvm.vp.load.nv16i8(ptr, <vscale x 16 x i1>, i32)
+declare <vscale x 2 x i64> @llvm.vp.load.nv2i64(ptr, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i64> @llvm.vp.load.nv4i64(ptr, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i64> @llvm.vp.load.nv8i64(ptr, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i64> @llvm.vp.load.nv16i64(ptr, <vscale x 16 x i1>, i32)
+
+declare void @llvm.vp.store.v2i8(<2 x i8>, ptr, <2 x i1>, i32)
+declare void @llvm.vp.store.v4i8(<4 x i8>, ptr, <4 x i1>, i32)
+declare void @llvm.vp.store.v8i8(<8 x i8>, ptr, <8 x i1>, i32)
+declare void @llvm.vp.store.v16i8(<16 x i8>, ptr, <16 x i1>, i32)
+declare void @llvm.vp.store.v2i64(<2 x i64>, ptr, <2 x i1>, i32)
+declare void @llvm.vp.store.v4i64(<4 x i64>, ptr, <4 x i1>, i32)
+declare void @llvm.vp.store.v8i64(<8 x i64>, ptr, <8 x i1>, i32)
+declare void @llvm.vp.store.v16i64(<16 x i64>, ptr, <16 x i1>, i32)
+declare void @llvm.vp.store.nv2i8(<vscale x 2 x i8>, ptr, <vscale x 2 x i1>, i32)
+declare void @llvm.vp.store.nv4i8(<vscale x 4 x i8>, ptr, <vscale x 4 x i1>, i32)
+declare void @llvm.vp.store.nv8i8(<vscale x 8 x i8>, ptr, <vscale x 8 x i1>, i32)
+declare void @llvm.vp.store.nv16i8(<vscale x 16 x i8>, ptr, <vscale x 16 x i1>, i32)
+declare void @llvm.vp.store.nv2i64(<vscale x 2 x i64>, ptr, <vscale x 2 x i1>, i32)
+declare void @llvm.vp.store.nv4i64(<vscale x 4 x i64>, ptr, <vscale x 4 x i1>, i32)
+declare void @llvm.vp.store.nv8i64(<vscale x 8 x i64>, ptr, <vscale x 8 x i1>, i32)
+declare void @llvm.vp.store.nv16i64(<vscale x 16 x i64>, ptr, <vscale x 16 x i1>, i32)
+
 declare <vscale x 1 x i32> @llvm.fshr.nxv4i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
 declare <vscale x 1 x i32> @llvm.fshl.nxv4i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
 



More information about the llvm-commits mailing list