[llvm] [X86] InstCombine: Generalize scalar SSE MAX/MIN intrinsics (PR #175375)

[Simon Pilgrim via llvm-commits]

================
@@ -0,0 +1,51 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt < %s -passes=instcombine -mtriple=x86_64-unknown-unknown -S | FileCheck %s
+
+define <4 x float> @test_max_ss_nan(<4 x float> %a) {
+  ; We pass a vector where the bottom element is NaN
+; CHECK-LABEL: define <4 x float> @test_max_ss_nan(
+; CHECK-SAME: <4 x float> [[A:%.*]]) {
+; CHECK-NEXT:    [[RES:%.*]] = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> [[A]], <4 x float> <float 0x7FF8000000000000, float poison, float poison, float poison>)
+; CHECK-NEXT:    ret <4 x float> [[RES]]
+;
+  %res = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> %a, <4 x float> <float 0x7FF8000000000000, float 0.0, float 0.0, float 0.0>)
+  ret <4 x float> %res
+}
+
+define <4 x float> @test_min_ss_inf(<4 x float> %a) {
+; CHECK-LABEL: define <4 x float> @test_min_ss_inf(
+; CHECK-SAME: <4 x float> [[A:%.*]]) {
+; CHECK-NEXT:    [[RES:%.*]] = call <4 x float> @llvm.x86.sse.min.ss(<4 x float> [[A]], <4 x float> <float 0x7FF0000000000000, float poison, float poison, float poison>)
+; CHECK-NEXT:    ret <4 x float> [[RES]]
+;
+  %res = call <4 x float> @llvm.x86.sse.min.ss(<4 x float> %a, <4 x float> <float 0x7FF0000000000000, float 0.0, float 0.0, float 0.0>)
+  ret <4 x float> %res
+}
+
+define <4 x float> @test_max_ss_neg_zero(<4 x float> %a) {
+; CHECK-LABEL: define <4 x float> @test_max_ss_neg_zero(
+; CHECK-SAME: <4 x float> [[A:%.*]]) {
+; CHECK-NEXT:    [[RES:%.*]] = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> [[A]], <4 x float> <float -0.000000e+00, float poison, float poison, float poison>)
+; CHECK-NEXT:    ret <4 x float> [[RES]]
+;
+  %res = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> %a, <4 x float> <float -0.0, float 0.0, float 0.0, float 0.0>)
+  ret <4 x float> %res
+}
+
+define <4 x float> @test_max_ss_variable_unsafe(<4 x float> %a, <4 x float> %b) {
+; CHECK-LABEL: define <4 x float> @test_max_ss_variable_unsafe(
+; CHECK-SAME: <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]) {
+; CHECK-NEXT:    [[RES:%.*]] = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> [[A]], <4 x float> [[B]])
+; CHECK-NEXT:    ret <4 x float> [[RES]]
+;
+  %res = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> %a, <4 x float> %b)
+  ret <4 x float> %res
+}
+
+define <4 x float> @test_max_ss_safe_constants() {
----------------
RKSimon wrote:

ideally we'd have another successful test that doesn't constant fold awya so we see the code expansion - maybe a sitofp conversion of an argument value from an `<2 x i32> to <2 x double>`  and then call sse2.min.sd against a constant value?

https://github.com/llvm/llvm-project/pull/175375