* Merged some functions into a single function, to make the costs more obvious.
* Moved scalable-mem-op-cost-model.ll -> sve-ldst.ll to be more consistent with other filenames.
+++ /dev/null
-; Checks if the memory cost model does not break when using scalable vectors
-
-; RUN: opt -cost-model -analyze -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
-
-define <vscale x 8 x i8> @load-sve-8(<vscale x 8 x i8>* %ptr) {
-; CHECK-LABEL: 'load-sve-8':
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:
- %retval = load <vscale x 8 x i8>, <vscale x 8 x i8>* %ptr
- ret <vscale x 8 x i8> %retval
-}
-
-define void @store-sve-8(<vscale x 8 x i8>* %ptr, <vscale x 8 x i8> %val) {
-; CHECK-LABEL: 'store-sve-8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:
- store <vscale x 8 x i8> %val, <vscale x 8 x i8>* %ptr
- ret void
-}
-
-define <vscale x 16 x i8> @load-sve-16(<vscale x 16 x i8>* %ptr) {
-; CHECK-LABEL: 'load-sve-16':
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:
- %retval = load <vscale x 16 x i8>, <vscale x 16 x i8>* %ptr
- ret <vscale x 16 x i8> %retval
-}
-
-define void @store-sve-16(<vscale x 16 x i8>* %ptr, <vscale x 16 x i8> %val) {
-; CHECK-LABEL: 'store-sve-16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:
- store <vscale x 16 x i8> %val, <vscale x 16 x i8>* %ptr
- ret void
-}
-
-define <vscale x 32 x i8> @load-sve-32(<vscale x 32 x i8>* %ptr) {
-; CHECK-LABEL: 'load-sve-32':
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:
- %retval = load <vscale x 32 x i8>, <vscale x 32 x i8>* %ptr
- ret <vscale x 32 x i8> %retval
-}
-
-define void @store-sve-32(<vscale x 32 x i8>* %ptr, <vscale x 32 x i8> %val) {
-; CHECK-LABEL: 'store-sve-32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:
- store <vscale x 32 x i8> %val, <vscale x 32 x i8>* %ptr
- ret void
-}
; RUN: opt -cost-model -analyze -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
-define <vscale x 4 x i32> @masked_gather_nxv4i32(<vscale x 4 x i32*> %ld, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru) {
-; CHECK-LABEL: 'masked_gather_nxv4i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 4 x i32> %res
- %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
- ret <vscale x 4 x i32> %res
+define void @masked_gathers(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %nxv8i1mask, <4 x i1> %v4i1mask, <1 x i1> %v1i1mask, <vscale x 1 x i1> %nxv1i1mask) {
+; CHECK-LABEL: 'masked_gathers'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32
+; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32
+; CHECK-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %res.v4i32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res.v1i128 = call <1 x i128> @llvm.masked.gather.v1i128.v1p0i128
+ %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
+ %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
+ %res.v4i32 = call <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> undef, i32 0, <4 x i1> %v4i1mask, <4 x i32> zeroinitializer)
+ %res.v1i128 = call <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*> undef, i32 0, <1 x i1> %v1i1mask, <1 x i128> zeroinitializer)
+ ret void
}
-define <vscale x 8 x i32> @masked_gather_nxv8i32(<vscale x 8 x i32*> %ld, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru) {
-; CHECK-LABEL: 'masked_gather_nxv8i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 8 x i32> %res
- %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x i32*> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
- ret <vscale x 8 x i32> %res
-}
-
-define <4 x i32> @masked_gather_v4i32(<4 x i32*> %ld, <4 x i1> %masks, <4 x i32> %passthru) {
-; CHECK-LABEL: 'masked_gather_v4i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
-
- %res = call <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
- ret <4 x i32> %res
-}
-
-; Check it properly falls back to BasicTTIImpl when legalized MVT is not a vector
-define <1 x i128> @masked_gather_v1i128(<1 x i128*> %ld, <1 x i1> %masks, <1 x i128> %passthru) {
-; CHECK-LABEL: 'masked_gather_v1i128'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <1 x i128> %res
-
- %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
- ret <1 x i128> %res
-}
-
-declare <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*> %ptrs, i32 %align, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
-declare <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x i32*> %ptrs, i32 %align, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
-declare <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> %ptrs, i32 %align, <4 x i1> %masks, <4 x i32> %passthru)
+declare <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*>, i32, <vscale x 4 x i1>, <vscale x 4 x i32>)
+declare <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x i32*>, i32, <vscale x 8 x i1>, <vscale x 8 x i32>)
+declare <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)
declare <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*>, i32, <1 x i1>, <1 x i128>)
-
--- /dev/null
+; RUN: opt -cost-model -analyze -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define void @scalable_loads() {
+; CHECK-LABEL: 'scalable_loads'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res.nxv8i8
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res.nxv16i8
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res.nxv32i8
+ %res.nxv8i8 = load <vscale x 8 x i8>, <vscale x 8 x i8>* undef
+ %res.nxv16i8 = load <vscale x 16 x i8>, <vscale x 16 x i8>* undef
+ %res.nxv32i8 = load <vscale x 32 x i8>, <vscale x 32 x i8>* undef
+ ret void
+}
+
+define void @scalable_stores() {
+; CHECK-LABEL: 'scalable_stores'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i8>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 16 x i8>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 32 x i8>
+ store <vscale x 8 x i8> undef, <vscale x 8 x i8>* undef
+ store <vscale x 16 x i8> undef, <vscale x 16 x i8>* undef
+ store <vscale x 32 x i8> undef, <vscale x 32 x i8>* undef
+ ret void
+}
; RUN: opt -cost-model -analyze -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
-define void @masked_scatter_nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, <vscale x 4 x i1> %masks) {
-; CHECK-LABEL: 'masked_scatter_nxv4i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 0, <vscale x 4 x i1> %masks)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
-
- call void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 0, <vscale x 4 x i1> %masks)
- ret void
-}
-
-define void @masked_scatter_nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, <vscale x 8 x i1> %masks) {
-; CHECK-LABEL: 'masked_scatter_nxv8i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, i32 0, <vscale x 8 x i1> %masks)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
-
- call void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, i32 0, <vscale x 8 x i1> %masks)
- ret void
-}
-
-define void @masked_scatter_v4i32(<4 x i32> %data, <4 x i32*> %ptrs, <4 x i1> %masks) {
-; CHECK-LABEL: 'masked_scatter_v4i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 29 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 0, <4 x i1> %masks)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
-
- call void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 0, <4 x i1> %masks)
- ret void
-}
-
-; Check it properly falls back to BasicTTIImpl when legalized MVT is not a vector
-define void @masked_scatter_v1i128(<1 x i128> %data, <1 x i128*> %ptrs, <1 x i1> %masks) {
-; CHECK-LABEL: 'masked_scatter_v1i128'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 0, <1 x i1> %masks)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
-
- call void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 0, <1 x i1> %masks)
+define void @masked_scatters(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %nxv8i1mask, <4 x i1> %v4i1mask, <1 x i1> %v1i1mask, <vscale x 1 x i1> %nxv1i1mask) {
+; CHECK-LABEL: 'masked_scatters'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32
+; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32
+; CHECK-NEXT: Cost Model: Found an estimated cost of 29 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v1i128.v1p0i128
+ call void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
+ call void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
+ call void @llvm.masked.scatter.v4i32(<4 x i32> undef, <4 x i32*> undef, i32 0, <4 x i1> %v4i1mask)
+ call void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> undef, <1 x i128*> undef, i32 0, <1 x i1> %v1i1mask)
ret void
}
-declare void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 %align, <vscale x 4 x i1> %masks)
-declare void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, i32 %align, <vscale x 8 x i1> %masks)
-declare void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 %align, <4 x i1> %masks)
-declare void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 %align, <1 x i1> %masks)
+declare void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32*>, i32, <vscale x 4 x i1>)
+declare void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32*>, i32, <vscale x 8 x i1>)
+declare void @llvm.masked.scatter.v4i32(<4 x i32>, <4 x i32*>, i32, <4 x i1>)
+declare void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128>, <1 x i128*>, i32, <1 x i1>)