[RISCV][NFC] Add tests for folds of ADDIs into load/stores

[luismarques]

Summary

This patch adds tests for folds of ADDIs into load/stores, focusing on load/stores with nonzero offsets.
When the offset is nonzero we currently don't do the fold. A follow-up patch will improve on that.

[lenary]

One nit, beyond that happy for this to land. Don't forget [NFC] in the title.

llvm/test/CodeGen/RISCV/fold-addi-loadstore.ll

136

I realise the code is the same, but it would be good to have tests for store to g_0, g_1, g_2 as well.

[luismarques]

llvm/test/CodeGen/RISCV/fold-addi-loadstore.ll

136

I tried to strike a balance between good coverage of the conceptual issue and too much repetition. It seemed like it was enough for one of the test types (loads) to thoroughly test all of the relevant offsets, while the other test types (stores, etc.) could focus on the boundary conditions, with one test where the fold shouldn't happen and one where it should. But I can include all of the combinations if you think that's beneficial for the patch.

[lenary]

Nice work, let's get this landed!

llvm/test/CodeGen/RISCV/fold-addi-loadstore.ll

136

Sounds reasonable to me!

llvm/test/CodeGen/RISCV/fold-addi-loadstore.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV32I %s
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV64I %s
+
+; We can often fold an ADDI into the offset of load/store instructions:
+;   (load (addi base, off1), off2) -> (load base, off1+off2)
+;   (store val, (addi base, off1), off2) -> (store val, base, off1+off2)
+; This is possible when the off1+off2 continues to fit the 12-bit immediate.
+; Check if we do the fold under various conditions. If off1 is (the low part of)
+; an address the fold's safety depends on the variable's alignment.
+
+@g_0 = global i64 0
+@g_1 = global i64 0, align 1
+@g_2 = global i64 0, align 2
+@g_4 = global i64 0, align 4
+@g_8 = global i64 0, align 8
+@g_16 = global i64 0, align 16
+
+define i64 @load_g_0() nounwind {
+; RV32I-LABEL: load_g_0:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a1, %hi(g_0)
+; RV32I-NEXT:    lw a0, %lo(g_0)(a1)
+; RV32I-NEXT:    addi a1, a1, %lo(g_0)
+; RV32I-NEXT:    lw a1, 4(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_g_0:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(g_0)
+; RV64I-NEXT:    ld a0, %lo(g_0)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* @g_0
+  ret i64 %0
+}
+
+define i64 @load_g_1() nounwind {
+; RV32I-LABEL: load_g_1:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a1, %hi(g_1)
+; RV32I-NEXT:    lw a0, %lo(g_1)(a1)
+; RV32I-NEXT:    addi a1, a1, %lo(g_1)
+; RV32I-NEXT:    lw a1, 4(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_g_1:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(g_1)
+; RV64I-NEXT:    ld a0, %lo(g_1)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* @g_1
+  ret i64 %0
+}
+
+define i64 @load_g_2() nounwind {
+; RV32I-LABEL: load_g_2:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a1, %hi(g_2)
+; RV32I-NEXT:    lw a0, %lo(g_2)(a1)
+; RV32I-NEXT:    addi a1, a1, %lo(g_2)
+; RV32I-NEXT:    lw a1, 4(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_g_2:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(g_2)
+; RV64I-NEXT:    ld a0, %lo(g_2)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* @g_2
+  ret i64 %0
+}
+
+define i64 @load_g_4() nounwind {
+; RV32I-LABEL: load_g_4:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a1, %hi(g_4)
+; RV32I-NEXT:    lw a0, %lo(g_4)(a1)
+; RV32I-NEXT:    addi a1, a1, %lo(g_4)
+; RV32I-NEXT:    lw a1, 4(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_g_4:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(g_4)
+; RV64I-NEXT:    ld a0, %lo(g_4)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* @g_4
+  ret i64 %0
+}
+
+define i64 @load_g_8() nounwind {
+; RV32I-LABEL: load_g_8:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a1, %hi(g_8)
+; RV32I-NEXT:    lw a0, %lo(g_8)(a1)
+; RV32I-NEXT:    addi a1, a1, %lo(g_8)
+; RV32I-NEXT:    lw a1, 4(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_g_8:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(g_8)
+; RV64I-NEXT:    ld a0, %lo(g_8)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* @g_8
+  ret i64 %0
+}
+
+define i64 @load_g_16() nounwind {
+; RV32I-LABEL: load_g_16:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a1, %hi(g_16)
+; RV32I-NEXT:    lw a0, %lo(g_16)(a1)
+; RV32I-NEXT:    addi a1, a1, %lo(g_16)
+; RV32I-NEXT:    lw a1, 4(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_g_16:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(g_16)
+; RV64I-NEXT:    ld a0, %lo(g_16)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* @g_16
+  ret i64 %0
+}
+
+define void @store_g_4() nounwind {
+; RV32I-LABEL: store_g_4:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a0, %hi(g_4)
+; RV32I-NEXT:    sw zero, %lo(g_4)(a0)
+; RV32I-NEXT:    addi a0, a0, %lo(g_4)
+; RV32I-NEXT:    sw zero, 4(a0)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: store_g_4:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(g_4)
+; RV64I-NEXT:    sd zero, %lo(g_4)(a0)
+; RV64I-NEXT:    ret
+entry:
+   store i64 0, i64* @g_4
+   ret void
+}
+
+define void @store_g_8() nounwind {
+; RV32I-LABEL: store_g_8:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a0, %hi(g_8)
+; RV32I-NEXT:    sw zero, %lo(g_8)(a0)
+; RV32I-NEXT:    addi a0, a0, %lo(g_8)
+; RV32I-NEXT:    sw zero, 4(a0)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: store_g_8:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(g_8)
+; RV64I-NEXT:    sd zero, %lo(g_8)(a0)
+; RV64I-NEXT:    ret
+entry:
+   store i64 0, i64* @g_8
+   ret void
+}
+
+; Check for folds in accesses to the second element of an i64 array.
+
+@ga_8 = dso_local local_unnamed_addr global [2 x i64] zeroinitializer, align 8
+@ga_16 = dso_local local_unnamed_addr global [2 x i64] zeroinitializer, align 16
+
+define i64 @load_ga_8() nounwind {
+; RV32I-LABEL: load_ga_8:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a0, %hi(ga_8)
+; RV32I-NEXT:    addi a1, a0, %lo(ga_8)
+; RV32I-NEXT:    lw a0, 8(a1)
+; RV32I-NEXT:    lw a1, 12(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_ga_8:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(ga_8+8)
+; RV64I-NEXT:    ld a0, %lo(ga_8+8)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* getelementptr inbounds ([2 x i64], [2 x i64]* @ga_8, i32 0, i32 1)
+  ret i64 %0
+}
+
+define i64 @load_ga_16() nounwind {
+; RV32I-LABEL: load_ga_16:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a0, %hi(ga_16)
+; RV32I-NEXT:    addi a1, a0, %lo(ga_16)
+; RV32I-NEXT:    lw a0, 8(a1)
+; RV32I-NEXT:    lw a1, 12(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_ga_16:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %hi(ga_16+8)
+; RV64I-NEXT:    ld a0, %lo(ga_16+8)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* getelementptr inbounds ([2 x i64], [2 x i64]* @ga_16, i32 0, i32 1)
+  ret i64 %0
+}
+
+; Check for folds in accesses to thread-local variables.
+
+@tl_4 = thread_local global i64 0, align 4
+@tl_8 = thread_local global i64 0, align 8
+
+define i64 @load_tl_4() nounwind {
+; RV32I-LABEL: load_tl_4:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a0, %tprel_hi(tl_4)
+; RV32I-NEXT:    add a1, a0, tp, %tprel_add(tl_4)
+; RV32I-NEXT:    lw a0, %tprel_lo(tl_4)(a1)
+; RV32I-NEXT:    addi a1, a1, %tprel_lo(tl_4)
+; RV32I-NEXT:    lw a1, 4(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_tl_4:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %tprel_hi(tl_4)
+; RV64I-NEXT:    add a0, a0, tp, %tprel_add(tl_4)
+; RV64I-NEXT:    ld a0, %tprel_lo(tl_4)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* @tl_4
+  ret i64 %0
+}
+
+define i64 @load_tl_8() nounwind {
+; RV32I-LABEL: load_tl_8:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a0, %tprel_hi(tl_8)
+; RV32I-NEXT:    add a1, a0, tp, %tprel_add(tl_8)
+; RV32I-NEXT:    lw a0, %tprel_lo(tl_8)(a1)
+; RV32I-NEXT:    addi a1, a1, %tprel_lo(tl_8)
+; RV32I-NEXT:    lw a1, 4(a1)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_tl_8:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    lui a0, %tprel_hi(tl_8)
+; RV64I-NEXT:    add a0, a0, tp, %tprel_add(tl_8)
+; RV64I-NEXT:    ld a0, %tprel_lo(tl_8)(a0)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* @tl_8
+  ret i64 %0
+}
+
+define i64 @load_const_ok() nounwind {
+; RV32I-LABEL: load_const_ok:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lw a0, 2040(zero)
+; RV32I-NEXT:    lw a1, 2044(zero)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_const_ok:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    ld a0, 2040(zero)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* inttoptr (i32 2040 to i64*)
+  ret i64 %0
+}
+
+define i64 @load_cost_overflow() nounwind {
+; RV32I-LABEL: load_cost_overflow:
+; RV32I:       # %bb.0: # %entry
+; RV32I-NEXT:    lui a0, 1
+; RV32I-NEXT:    lw a1, -2048(a0)
+; RV32I-NEXT:    lw a0, 2044(zero)
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: load_cost_overflow:
+; RV64I:       # %bb.0: # %entry
+; RV64I-NEXT:    ld a0, 2044(zero)
+; RV64I-NEXT:    ret
+entry:
+  %0 = load i64, i64* inttoptr (i64 2044 to i64*)
+  ret i64 %0
+}