[llvm] AMDGPU: Pre-commit test to verify mode change in fp constrained operations (PR #88858)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 %s -o - | FileCheck -check-prefix=GCN %s
+
+; The si-mode-register pass is changing the default mode for FP constrained  operations.
+; It must ignore for strictfp functions.
+
+define double @ignoreStrictfp(double noundef %a, double noundef %b) #0 {
+; GCN-LABEL: ignoreStrictfp:
+; GCN:       ; %bb.0:
+; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 2, 2), 1
+; GCN-NEXT:    s_nop 1
+; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 2, 1), 0
+; GCN-NEXT:    v_add_f64 v[0:1], v[0:1], v[2:3]
+; GCN-NEXT:    s_setpc_b64 s[30:31]
+  tail call void @llvm.amdgcn.s.setreg(i32 2177, i32 1)
+  %val = tail call double @llvm.experimental.constrained.fadd.f64(double %a, double %b, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
+  ret double %val
+}
+
+define double @set_fpenv(double noundef %a, double noundef %b) #0 {
+; GCN-LABEL: set_fpenv:
+; GCN:       ; %bb.0: ; %entry
+; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 0, 23), 4
+; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_TRAPSTS, 0, 5), 0
+; GCN-NEXT:    s_nop 0
+; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 2, 1), 0
+; GCN-NEXT:    v_add_f64 v[0:1], v[0:1], v[2:3]
+; GCN-NEXT:    s_setpc_b64 s[30:31]
+entry:
+  call void @llvm.set.fpenv.i64(i64 4)
----------------
arsenm wrote:

Not the most realistic source value but ok 

https://github.com/llvm/llvm-project/pull/88858