[llvm] [WebAssembly] Constant fold wasm.dot (PR #149619)

[Luke Lau via llvm-commits]

================
@@ -0,0 +1,62 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+
+; RUN: opt -passes=instsimplify -S < %s | FileCheck %s
+
+; Test that intrinsics wasm dot call are constant folded
+
+target triple = "wasm32-unknown-unknown"
+
+
+define <4 x i32> @dot_zero() {
+; CHECK-LABEL: define <4 x i32> @dot_zero() {
+; CHECK-NEXT:    ret <4 x i32> zeroinitializer
+;
+  %res = tail call <4 x i32> @llvm.wasm.dot(<8 x i16> zeroinitializer, <8 x i16> zeroinitializer)
+  ret <4 x i32> %res
+}
+
+; a               =   1    2    3    4    5    6    7    8
+; b               =   1    2    3    4    5    6    7    8
+; k1|k2 = a * b   =   1    4    9   16   25   36   49   64
+; k1 + k2         =   (1+4) |  (9 + 16) | (25 + 36)  | (49 + 64)
+; result          =    5    |   25    |   61    |   113
+define <4 x i32> @dot_nonzero() {
+; CHECK-LABEL: define <4 x i32> @dot_nonzero() {
+; CHECK-NEXT:    ret <4 x i32> <i32 5, i32 25, i32 61, i32 113>
+;
+  %res = tail call <4 x i32> @llvm.wasm.dot(<8 x i16> <i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8>, <8 x i16> <i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8>)
+  ret <4 x i32> %res
+}
+
+define <4 x i32> @dot_doubly_negative() {
+; CHECK-LABEL: define <4 x i32> @dot_doubly_negative() {
+; CHECK-NEXT:    ret <4 x i32> splat (i32 2)
+;
+  %res = tail call <4 x i32> @llvm.wasm.dot(<8 x i16> <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>, <8 x i16> <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>)
+  ret <4 x i32> %res
+}
+
+; This test checks for llvm's compliance on spec's wasm.dot's imul and iadd
+; Since the original number can only be i16::max == 2^15 - 1,
+;   subsequent modulo of 2^32 of imul and iadd
+;   should return the same result
+; 2*(2^15 - 1)^2 % 2^32 == 2*(2^15 - 1)^2
+define <4 x i32> @dot_follow_modulo_spec_1() {
+; CHECK-LABEL: define <4 x i32> @dot_follow_modulo_spec_1() {
+; CHECK-NEXT:    ret <4 x i32> <i32 2147352578, i32 0, i32 0, i32 0>
+;
+  %res = tail call <4 x i32> @llvm.wasm.dot(<8 x i16> <i16 32767, i16 32767, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>, <8 x i16> <i16 32767, i16 32767, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>)
+  ret <4 x i32> %res
+}
+
+; This test checks for llvm's compliance on spec's wasm.dot's imul and iadd
+; 2*(- 2^15)^2 == 2^31, doesn't exceed 2^32 so we don't have to mod
+; wrapping around is -(2^31), still doesn't exceed 2^32
----------------
lukel97 wrote:

I don't think we need to mention the spec in this comment, we can just say something like "test i16 max signed values fit in i32"

https://github.com/llvm/llvm-project/pull/149619