[llvm] [Matrix] Add tests identifying GVN and DSE opportunities for matrix store / load intrinsics (PR #163573)

[Florian Hahn via llvm-commits]

================
@@ -0,0 +1,85 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -passes=gvn -S %s | FileCheck %s
+
+define <8 x double> @redundant_unstrided_load(ptr %src) {
+; CHECK-LABEL: define <8 x double> @redundant_unstrided_load(
+; CHECK-SAME: ptr [[SRC:%.*]]) {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[SRC_OFFSET:%.*]] = getelementptr inbounds double, ptr [[SRC]], i32 8
+; CHECK-NEXT:    [[L:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC_OFFSET]], i32 4, i1 false, i32 4, i32 2)
+; CHECK-NEXT:    call void @llvm.matrix.column.major.store.v8f64.i32(<8 x double> [[L]], ptr [[SRC]], i32 4, i1 false, i32 4, i32 2)
+; CHECK-NEXT:    [[L_2:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC_OFFSET]], i32 4, i1 false, i32 4, i32 2)
+; CHECK-NEXT:    [[S:%.*]] = fadd <8 x double> [[L]], [[L_2]]
+; CHECK-NEXT:    ret <8 x double> [[S]]
+;
+entry:
+  %src.offset = getelementptr inbounds double, ptr %src, i32 8
+  %l = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 4, i1 false, i32 4, i32 2)
+  call void @llvm.matrix.column.major.store(<8 x double> %l, ptr %src, i32 4, i1 false, i32 4, i32 2)
+  %l.2 = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 4, i1 false, i32 4, i32 2)
+  %s = fadd <8 x double> %l, %l.2
+  ret <8 x double> %s
+}
+
+define <8 x double> @redundant_unstrided_load_non_matrix_store(ptr %src) {
+; CHECK-LABEL: define <8 x double> @redundant_unstrided_load_non_matrix_store(
+; CHECK-SAME: ptr [[SRC:%.*]]) {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[SRC_OFFSET:%.*]] = getelementptr inbounds double, ptr [[SRC]], i32 8
+; CHECK-NEXT:    [[L:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC_OFFSET]], i32 4, i1 false, i32 4, i32 2)
+; CHECK-NEXT:    store double 4.200000e+01, ptr [[SRC]], align 8
+; CHECK-NEXT:    [[L_2:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC_OFFSET]], i32 4, i1 false, i32 4, i32 2)
+; CHECK-NEXT:    [[S:%.*]] = fadd <8 x double> [[L]], [[L_2]]
+; CHECK-NEXT:    ret <8 x double> [[S]]
+;
+entry:
+  %src.offset = getelementptr inbounds double, ptr %src, i32 8
+  %l = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 4, i1 false, i32 4, i32 2)
----------------
fhahn wrote:

can use a tigther offset here (1 should be sufficient)

https://github.com/llvm/llvm-project/pull/163573