[llvm] f7c3309 - [RISCV] Add coverage for <N x i1> vp.strided.load

[Philip Reames via llvm-commits]

Author: Philip Reames
Date: 2024-09-20T10:30:21-07:00
New Revision: f7c3309b1361443cded697255995fade24838ef8

URL: https://github.com/llvm/llvm-project/commit/f7c3309b1361443cded697255995fade24838ef8
DIFF: https://github.com/llvm/llvm-project/commit/f7c3309b1361443cded697255995fade24838ef8.diff

LOG: [RISCV] Add coverage for <N x i1> vp.strided.load

These are currently scalarized, and I need something to exercise
<N x i1> scalarization costing.  We should probably consider adding
a buildvector intrinsic for this purpose.

Added: 
    

Modified: 
    llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll

Removed: 
    


################################################################################
diff  --git a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
index 49e09a4e5fead1..807657797288da 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
@@ -1029,6 +1029,10 @@ define void @store() {
 
 define void @strided_load() {
 ; CHECK-LABEL: 'strided_load'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %ti1_2 = call <2 x i1> @llvm.experimental.vp.strided.load.v2i1.p0.i64(ptr undef, i64 undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %ti1_4 = call <4 x i1> @llvm.experimental.vp.strided.load.v4i1.p0.i64(ptr undef, i64 undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %ti1_8 = call <8 x i1> @llvm.experimental.vp.strided.load.v8i1.p0.i64(ptr undef, i64 undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 142 for instruction: %ti1_16 = call <16 x i1> @llvm.experimental.vp.strided.load.v16i1.p0.i64(ptr undef, i64 undef, <16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t0 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr undef, i64 undef, <2 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t2 = call <4 x i8> @llvm.experimental.vp.strided.load.v4i8.p0.i64(ptr undef, i64 undef, <4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t4 = call <8 x i8> @llvm.experimental.vp.strided.load.v8i8.p0.i64(ptr undef, i64 undef, <8 x i1> undef, i32 undef)
@@ -1052,6 +1056,10 @@ define void @strided_load() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPEBASED-LABEL: 'strided_load'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %ti1_2 = call <2 x i1> @llvm.experimental.vp.strided.load.v2i1.p0.i64(ptr undef, i64 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %ti1_4 = call <4 x i1> @llvm.experimental.vp.strided.load.v4i1.p0.i64(ptr undef, i64 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %ti1_8 = call <8 x i1> @llvm.experimental.vp.strided.load.v8i1.p0.i64(ptr undef, i64 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 174 for instruction: %ti1_16 = call <16 x i1> @llvm.experimental.vp.strided.load.v16i1.p0.i64(ptr undef, i64 undef, <16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %t0 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr undef, i64 undef, <2 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %t2 = call <4 x i8> @llvm.experimental.vp.strided.load.v4i8.p0.i64(ptr undef, i64 undef, <4 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %t4 = call <8 x i8> @llvm.experimental.vp.strided.load.v8i8.p0.i64(ptr undef, i64 undef, <8 x i1> undef, i32 undef)
@@ -1074,6 +1082,10 @@ define void @strided_load() {
 ; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t31 = call <vscale x 16 x i64> @llvm.experimental.vp.strided.load.nxv16i64.p0.i64(ptr undef, i64 undef, <vscale x 16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+  %ti1_2 = call <2 x i1> @llvm.experimental.vp.strided.load.v2i1.i64(ptr undef, i64 undef, <2 x i1> undef, i32 undef)
+  %ti1_4 = call <4 x i1> @llvm.experimental.vp.strided.load.v4i1.i64(ptr undef, i64 undef, <4 x i1> undef, i32 undef)
+  %ti1_8 = call <8 x i1> @llvm.experimental.vp.strided.load.v8i1.i64(ptr undef, i64 undef, <8 x i1> undef, i32 undef)
+  %ti1_16 = call <16 x i1> @llvm.experimental.vp.strided.load.v16i1.i64(ptr undef, i64 undef, <16 x i1> undef, i32 undef)
   %t0 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.i64(ptr undef, i64 undef, <2 x i1> undef, i32 undef)
   %t2 = call <4 x i8> @llvm.experimental.vp.strided.load.v4i8.i64(ptr undef, i64 undef, <4 x i1> undef, i32 undef)
   %t4 = call <8 x i8> @llvm.experimental.vp.strided.load.v8i8.i64(ptr undef, i64 undef, <8 x i1> undef, i32 undef)