[AArch64][llvm] Pre-commit tests for #137703 (NFC) #137702
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-backend-aarch64 Author: Jonathan Thackray (jthackray) ChangesAdd pre-commit tests for lowering atomicrmw Patch is 153.26 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/137702.diff 5 Files Affected:
diff --git a/llvm/test/CodeGen/AArch64/Atomics/aarch64-atomicrmw-lsfe.ll b/llvm/test/CodeGen/AArch64/Atomics/aarch64-atomicrmw-lsfe.ll
index ef1f11e71f433..7ee2a0bb19c0e 100644
--- a/llvm/test/CodeGen/AArch64/Atomics/aarch64-atomicrmw-lsfe.ll
+++ b/llvm/test/CodeGen/AArch64/Atomics/aarch64-atomicrmw-lsfe.ll
@@ -1598,3 +1598,1207 @@ define dso_local double @atomicrmw_fmin_double_unaligned_seq_cst(ptr %ptr, doubl
%r = atomicrmw fmin ptr %ptr, double %value seq_cst, align 1
ret double %r
}
+
+define dso_local half @atomicrmw_fmaximum_half_aligned_monotonic(ptr %ptr, half %value) {
+; -O0-LABEL: atomicrmw_fmaximum_half_aligned_monotonic:
+; -O0: ldaxrh w0, [x9]
+; -O0: cmp w0, w10, uxth
+; -O0: stlxrh w8, w11, [x9]
+; -O0: subs w8, w8, w0, uxth
+;
+; -O1-LABEL: atomicrmw_fmaximum_half_aligned_monotonic:
+; -O1: ldxrh w8, [x0]
+; -O1: stxrh w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, half %value monotonic, align 2
+ ret half %r
+}
+
+define dso_local void @atomicrmw_fmaximum_half_aligned_monotonic_unused(ptr %ptr, half %value) {
+; -O0-LABEL: atomicrmw_fmaximum_half_aligned_monotonic_unused:
+; -O0: ldaxrh w0, [x9]
+; -O0: cmp w0, w10, uxth
+; -O0: stlxrh w8, w11, [x9]
+; -O0: subs w8, w8, w0, uxth
+;
+; -O1-LABEL: atomicrmw_fmaximum_half_aligned_monotonic_unused:
+; -O1: ldxrh w8, [x0]
+; -O1: stxrh w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, half %value monotonic, align 2
+ ret void
+}
+
+define dso_local half @atomicrmw_fmaximum_half_aligned_acquire(ptr %ptr, half %value) {
+; -O0-LABEL: atomicrmw_fmaximum_half_aligned_acquire:
+; -O0: ldaxrh w0, [x9]
+; -O0: cmp w0, w10, uxth
+; -O0: stlxrh w8, w11, [x9]
+; -O0: subs w8, w8, w0, uxth
+;
+; -O1-LABEL: atomicrmw_fmaximum_half_aligned_acquire:
+; -O1: ldaxrh w8, [x0]
+; -O1: stxrh w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, half %value acquire, align 2
+ ret half %r
+}
+
+define dso_local half @atomicrmw_fmaximum_half_aligned_release(ptr %ptr, half %value) {
+; -O0-LABEL: atomicrmw_fmaximum_half_aligned_release:
+; -O0: ldaxrh w0, [x9]
+; -O0: cmp w0, w10, uxth
+; -O0: stlxrh w8, w11, [x9]
+; -O0: subs w8, w8, w0, uxth
+;
+; -O1-LABEL: atomicrmw_fmaximum_half_aligned_release:
+; -O1: ldxrh w8, [x0]
+; -O1: stlxrh w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, half %value release, align 2
+ ret half %r
+}
+
+define dso_local void @atomicrmw_fmaximum_half_aligned_release_unused(ptr %ptr, half %value) {
+; -O0-LABEL: atomicrmw_fmaximum_half_aligned_release_unused:
+; -O0: ldaxrh w0, [x9]
+; -O0: cmp w0, w10, uxth
+; -O0: stlxrh w8, w11, [x9]
+; -O0: subs w8, w8, w0, uxth
+;
+; -O1-LABEL: atomicrmw_fmaximum_half_aligned_release_unused:
+; -O1: ldxrh w8, [x0]
+; -O1: stlxrh w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, half %value release, align 2
+ ret void
+}
+
+define dso_local half @atomicrmw_fmaximum_half_aligned_acq_rel(ptr %ptr, half %value) {
+; -O0-LABEL: atomicrmw_fmaximum_half_aligned_acq_rel:
+; -O0: ldaxrh w0, [x9]
+; -O0: cmp w0, w10, uxth
+; -O0: stlxrh w8, w11, [x9]
+; -O0: subs w8, w8, w0, uxth
+;
+; -O1-LABEL: atomicrmw_fmaximum_half_aligned_acq_rel:
+; -O1: ldaxrh w8, [x0]
+; -O1: stlxrh w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, half %value acq_rel, align 2
+ ret half %r
+}
+
+define dso_local half @atomicrmw_fmaximum_half_aligned_seq_cst(ptr %ptr, half %value) {
+; -O0-LABEL: atomicrmw_fmaximum_half_aligned_seq_cst:
+; -O0: ldaxrh w0, [x9]
+; -O0: cmp w0, w10, uxth
+; -O0: stlxrh w8, w11, [x9]
+; -O0: subs w8, w8, w0, uxth
+;
+; -O1-LABEL: atomicrmw_fmaximum_half_aligned_seq_cst:
+; -O1: ldaxrh w8, [x0]
+; -O1: stlxrh w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, half %value seq_cst, align 2
+ ret half %r
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_aligned_monotonic(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_aligned_monotonic:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: ldaxrh w9, [x11]
+; -O0: cmp w9, w8, uxth
+; -O0: stlxrh w10, w12, [x11]
+; -O0: subs w8, w9, w8, uxth
+; -O0: subs w8, w8, #1
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_aligned_monotonic:
+; -O1: ldxrh w9, [x0]
+; -O1: add w9, w9, w8
+; -O1: add w9, w10, w9
+; -O1: stxrh w10, w9, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value monotonic, align 2
+ ret bfloat %r
+}
+
+define dso_local void @atomicrmw_fmaximum_bfloat_aligned_monotonic_unused(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_aligned_monotonic_unused:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: ldaxrh w9, [x11]
+; -O0: cmp w9, w8, uxth
+; -O0: stlxrh w10, w12, [x11]
+; -O0: subs w8, w9, w8, uxth
+; -O0: subs w8, w8, #1
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_aligned_monotonic_unused:
+; -O1: ldxrh w9, [x0]
+; -O1: add w9, w9, w8
+; -O1: add w9, w10, w9
+; -O1: stxrh w10, w9, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value monotonic, align 2
+ ret void
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_aligned_acquire(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_aligned_acquire:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: ldaxrh w9, [x11]
+; -O0: cmp w9, w8, uxth
+; -O0: stlxrh w10, w12, [x11]
+; -O0: subs w8, w9, w8, uxth
+; -O0: subs w8, w8, #1
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_aligned_acquire:
+; -O1: ldaxrh w9, [x0]
+; -O1: add w9, w9, w8
+; -O1: add w9, w10, w9
+; -O1: stxrh w10, w9, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value acquire, align 2
+ ret bfloat %r
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_aligned_release(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_aligned_release:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: ldaxrh w9, [x11]
+; -O0: cmp w9, w8, uxth
+; -O0: stlxrh w10, w12, [x11]
+; -O0: subs w8, w9, w8, uxth
+; -O0: subs w8, w8, #1
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_aligned_release:
+; -O1: ldxrh w9, [x0]
+; -O1: add w9, w9, w8
+; -O1: add w9, w10, w9
+; -O1: stlxrh w10, w9, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value release, align 2
+ ret bfloat %r
+}
+
+define dso_local void @atomicrmw_fmaximum_bfloat_aligned_release_unused(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_aligned_release_unused:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: ldaxrh w9, [x11]
+; -O0: cmp w9, w8, uxth
+; -O0: stlxrh w10, w12, [x11]
+; -O0: subs w8, w9, w8, uxth
+; -O0: subs w8, w8, #1
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_aligned_release_unused:
+; -O1: ldxrh w9, [x0]
+; -O1: add w9, w9, w8
+; -O1: add w9, w10, w9
+; -O1: stlxrh w10, w9, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value release, align 2
+ ret void
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_aligned_acq_rel(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_aligned_acq_rel:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: ldaxrh w9, [x11]
+; -O0: cmp w9, w8, uxth
+; -O0: stlxrh w10, w12, [x11]
+; -O0: subs w8, w9, w8, uxth
+; -O0: subs w8, w8, #1
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_aligned_acq_rel:
+; -O1: ldaxrh w9, [x0]
+; -O1: add w9, w9, w8
+; -O1: add w9, w10, w9
+; -O1: stlxrh w10, w9, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value acq_rel, align 2
+ ret bfloat %r
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_aligned_seq_cst(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_aligned_seq_cst:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: ldaxrh w9, [x11]
+; -O0: cmp w9, w8, uxth
+; -O0: stlxrh w10, w12, [x11]
+; -O0: subs w8, w9, w8, uxth
+; -O0: subs w8, w8, #1
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_aligned_seq_cst:
+; -O1: ldaxrh w9, [x0]
+; -O1: add w9, w9, w8
+; -O1: add w9, w10, w9
+; -O1: stlxrh w10, w9, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value seq_cst, align 2
+ ret bfloat %r
+}
+
+define dso_local float @atomicrmw_fmaximum_float_aligned_monotonic(ptr %ptr, float %value) {
+; -O0-LABEL: atomicrmw_fmaximum_float_aligned_monotonic:
+; -O0: ldaxr w0, [x9]
+; -O0: cmp w0, w10
+; -O0: stlxr w8, w11, [x9]
+; -O0: subs w8, w0, w8
+;
+; -O1-LABEL: atomicrmw_fmaximum_float_aligned_monotonic:
+; -O1: ldxr w8, [x0]
+; -O1: stxr w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, float %value monotonic, align 4
+ ret float %r
+}
+
+define dso_local void @atomicrmw_fmaximum_float_aligned_monotonic_unused(ptr %ptr, float %value) {
+; -O0-LABEL: atomicrmw_fmaximum_float_aligned_monotonic_unused:
+; -O0: ldaxr w0, [x9]
+; -O0: cmp w0, w10
+; -O0: stlxr w8, w11, [x9]
+; -O0: subs w8, w0, w8
+;
+; -O1-LABEL: atomicrmw_fmaximum_float_aligned_monotonic_unused:
+; -O1: ldxr w8, [x0]
+; -O1: stxr w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, float %value monotonic, align 4
+ ret void
+}
+
+define dso_local float @atomicrmw_fmaximum_float_aligned_acquire(ptr %ptr, float %value) {
+; -O0-LABEL: atomicrmw_fmaximum_float_aligned_acquire:
+; -O0: ldaxr w0, [x9]
+; -O0: cmp w0, w10
+; -O0: stlxr w8, w11, [x9]
+; -O0: subs w8, w0, w8
+;
+; -O1-LABEL: atomicrmw_fmaximum_float_aligned_acquire:
+; -O1: ldaxr w8, [x0]
+; -O1: stxr w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, float %value acquire, align 4
+ ret float %r
+}
+
+define dso_local float @atomicrmw_fmaximum_float_aligned_release(ptr %ptr, float %value) {
+; -O0-LABEL: atomicrmw_fmaximum_float_aligned_release:
+; -O0: ldaxr w0, [x9]
+; -O0: cmp w0, w10
+; -O0: stlxr w8, w11, [x9]
+; -O0: subs w8, w0, w8
+;
+; -O1-LABEL: atomicrmw_fmaximum_float_aligned_release:
+; -O1: ldxr w8, [x0]
+; -O1: stlxr w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, float %value release, align 4
+ ret float %r
+}
+
+define dso_local void @atomicrmw_fmaximum_float_aligned_release_unused(ptr %ptr, float %value) {
+; -O0-LABEL: atomicrmw_fmaximum_float_aligned_release_unused:
+; -O0: ldaxr w0, [x9]
+; -O0: cmp w0, w10
+; -O0: stlxr w8, w11, [x9]
+; -O0: subs w8, w0, w8
+;
+; -O1-LABEL: atomicrmw_fmaximum_float_aligned_release_unused:
+; -O1: ldxr w8, [x0]
+; -O1: stlxr w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, float %value release, align 4
+ ret void
+}
+
+define dso_local float @atomicrmw_fmaximum_float_aligned_acq_rel(ptr %ptr, float %value) {
+; -O0-LABEL: atomicrmw_fmaximum_float_aligned_acq_rel:
+; -O0: ldaxr w0, [x9]
+; -O0: cmp w0, w10
+; -O0: stlxr w8, w11, [x9]
+; -O0: subs w8, w0, w8
+;
+; -O1-LABEL: atomicrmw_fmaximum_float_aligned_acq_rel:
+; -O1: ldaxr w8, [x0]
+; -O1: stlxr w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, float %value acq_rel, align 4
+ ret float %r
+}
+
+define dso_local float @atomicrmw_fmaximum_float_aligned_seq_cst(ptr %ptr, float %value) {
+; -O0-LABEL: atomicrmw_fmaximum_float_aligned_seq_cst:
+; -O0: ldaxr w0, [x9]
+; -O0: cmp w0, w10
+; -O0: stlxr w8, w11, [x9]
+; -O0: subs w8, w0, w8
+;
+; -O1-LABEL: atomicrmw_fmaximum_float_aligned_seq_cst:
+; -O1: ldaxr w8, [x0]
+; -O1: stlxr w9, w8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, float %value seq_cst, align 4
+ ret float %r
+}
+
+define dso_local double @atomicrmw_fmaximum_double_aligned_monotonic(ptr %ptr, double %value) {
+; -O0-LABEL: atomicrmw_fmaximum_double_aligned_monotonic:
+; -O0: ldaxr x0, [x9]
+; -O0: cmp x0, x10
+; -O0: stlxr w8, x11, [x9]
+; -O0: subs x8, x0, x8
+;
+; -O1-LABEL: atomicrmw_fmaximum_double_aligned_monotonic:
+; -O1: ldxr x8, [x0]
+; -O1: stxr w9, x8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, double %value monotonic, align 8
+ ret double %r
+}
+
+define dso_local void @atomicrmw_fmaximum_double_aligned_monotonic_unused(ptr %ptr, double %value) {
+; -O0-LABEL: atomicrmw_fmaximum_double_aligned_monotonic_unused:
+; -O0: ldaxr x0, [x9]
+; -O0: cmp x0, x10
+; -O0: stlxr w8, x11, [x9]
+; -O0: subs x8, x0, x8
+;
+; -O1-LABEL: atomicrmw_fmaximum_double_aligned_monotonic_unused:
+; -O1: ldxr x8, [x0]
+; -O1: stxr w9, x8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, double %value monotonic, align 8
+ ret void
+}
+
+define dso_local double @atomicrmw_fmaximum_double_aligned_acquire(ptr %ptr, double %value) {
+; -O0-LABEL: atomicrmw_fmaximum_double_aligned_acquire:
+; -O0: ldaxr x0, [x9]
+; -O0: cmp x0, x10
+; -O0: stlxr w8, x11, [x9]
+; -O0: subs x8, x0, x8
+;
+; -O1-LABEL: atomicrmw_fmaximum_double_aligned_acquire:
+; -O1: ldaxr x8, [x0]
+; -O1: stxr w9, x8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, double %value acquire, align 8
+ ret double %r
+}
+
+define dso_local double @atomicrmw_fmaximum_double_aligned_release(ptr %ptr, double %value) {
+; -O0-LABEL: atomicrmw_fmaximum_double_aligned_release:
+; -O0: ldaxr x0, [x9]
+; -O0: cmp x0, x10
+; -O0: stlxr w8, x11, [x9]
+; -O0: subs x8, x0, x8
+;
+; -O1-LABEL: atomicrmw_fmaximum_double_aligned_release:
+; -O1: ldxr x8, [x0]
+; -O1: stlxr w9, x8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, double %value release, align 8
+ ret double %r
+}
+
+define dso_local void @atomicrmw_fmaximum_double_aligned_release_unused(ptr %ptr, double %value) {
+; -O0-LABEL: atomicrmw_fmaximum_double_aligned_release_unused:
+; -O0: ldaxr x0, [x9]
+; -O0: cmp x0, x10
+; -O0: stlxr w8, x11, [x9]
+; -O0: subs x8, x0, x8
+;
+; -O1-LABEL: atomicrmw_fmaximum_double_aligned_release_unused:
+; -O1: ldxr x8, [x0]
+; -O1: stlxr w9, x8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, double %value release, align 8
+ ret void
+}
+
+define dso_local double @atomicrmw_fmaximum_double_aligned_acq_rel(ptr %ptr, double %value) {
+; -O0-LABEL: atomicrmw_fmaximum_double_aligned_acq_rel:
+; -O0: ldaxr x0, [x9]
+; -O0: cmp x0, x10
+; -O0: stlxr w8, x11, [x9]
+; -O0: subs x8, x0, x8
+;
+; -O1-LABEL: atomicrmw_fmaximum_double_aligned_acq_rel:
+; -O1: ldaxr x8, [x0]
+; -O1: stlxr w9, x8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, double %value acq_rel, align 8
+ ret double %r
+}
+
+define dso_local double @atomicrmw_fmaximum_double_aligned_seq_cst(ptr %ptr, double %value) {
+; -O0-LABEL: atomicrmw_fmaximum_double_aligned_seq_cst:
+; -O0: ldaxr x0, [x9]
+; -O0: cmp x0, x10
+; -O0: stlxr w8, x11, [x9]
+; -O0: subs x8, x0, x8
+;
+; -O1-LABEL: atomicrmw_fmaximum_double_aligned_seq_cst:
+; -O1: ldaxr x8, [x0]
+; -O1: stlxr w9, x8, [x0]
+ %r = atomicrmw fmaximum ptr %ptr, double %value seq_cst, align 8
+ ret double %r
+}
+
+define dso_local half @atomicrmw_fmaximum_half_unaligned_monotonic(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_half_unaligned_monotonic:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, half %value monotonic, align 1
+ ret half %r
+}
+
+define dso_local half @atomicrmw_fmaximum_half_unaligned_acquire(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_half_unaligned_acquire:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, half %value acquire, align 1
+ ret half %r
+}
+
+define dso_local half @atomicrmw_fmaximum_half_unaligned_release(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_half_unaligned_release:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, half %value release, align 1
+ ret half %r
+}
+
+define dso_local half @atomicrmw_fmaximum_half_unaligned_acq_rel(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_half_unaligned_acq_rel:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, half %value acq_rel, align 1
+ ret half %r
+}
+
+define dso_local half @atomicrmw_fmaximum_half_unaligned_seq_cst(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_half_unaligned_seq_cst:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, half %value seq_cst, align 1
+ ret half %r
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_unaligned_monotonic(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_unaligned_monotonic:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: bl __atomic_compare_exchange
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_unaligned_monotonic:
+; -O1: add w8, w8, w20
+; -O1: add w8, w9, w8
+; -O1: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value monotonic, align 1
+ ret bfloat %r
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_unaligned_acquire(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_unaligned_acquire:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: bl __atomic_compare_exchange
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_unaligned_acquire:
+; -O1: add w8, w8, w20
+; -O1: add w8, w9, w8
+; -O1: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value acquire, align 1
+ ret bfloat %r
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_unaligned_release(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_unaligned_release:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: bl __atomic_compare_exchange
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_unaligned_release:
+; -O1: add w8, w8, w20
+; -O1: add w8, w9, w8
+; -O1: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value release, align 1
+ ret bfloat %r
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_unaligned_acq_rel(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_unaligned_acq_rel:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: bl __atomic_compare_exchange
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_unaligned_acq_rel:
+; -O1: add w8, w8, w20
+; -O1: add w8, w9, w8
+; -O1: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value acq_rel, align 1
+ ret bfloat %r
+}
+
+define dso_local bfloat @atomicrmw_fmaximum_bfloat_unaligned_seq_cst(ptr %ptr, bfloat %value) {
+; -O0-LABEL: atomicrmw_fmaximum_bfloat_unaligned_seq_cst:
+; -O0: add w8, w8, w9
+; -O0: add w8, w8, w9
+; -O0: bl __atomic_compare_exchange
+;
+; -O1-LABEL: atomicrmw_fmaximum_bfloat_unaligned_seq_cst:
+; -O1: add w8, w8, w20
+; -O1: add w8, w9, w8
+; -O1: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, bfloat %value seq_cst, align 1
+ ret bfloat %r
+}
+
+define dso_local float @atomicrmw_fmaximum_float_unaligned_monotonic(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_float_unaligned_monotonic:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, float %value monotonic, align 1
+ ret float %r
+}
+
+define dso_local float @atomicrmw_fmaximum_float_unaligned_acquire(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_float_unaligned_acquire:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, float %value acquire, align 1
+ ret float %r
+}
+
+define dso_local float @atomicrmw_fmaximum_float_unaligned_release(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_float_unaligned_release:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, float %value release, align 1
+ ret float %r
+}
+
+define dso_local float @atomicrmw_fmaximum_float_unaligned_acq_rel(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_float_unaligned_acq_rel:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, float %value acq_rel, align 1
+ ret float %r
+}
+
+define dso_local float @atomicrmw_fmaximum_float_unaligned_seq_cst(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_float_unaligned_seq_cst:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, float %value seq_cst, align 1
+ ret float %r
+}
+
+define dso_local double @atomicrmw_fmaximum_double_unaligned_monotonic(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fmaximum_double_unaligned_monotonic:
+; CHECK: bl __atomic_compare_exchange
+ %r = atomicrmw fmaximum ptr %ptr, double %value monotonic, align 1
+ ret double %r
+}
+
+defin...
[truncated]
|
There was a problem hiding this comment.
Should I look at the ABI to understand if these tests are lowering properly?
Like in here:
https://github.com/ARM-software/abi-aa/blob/main/atomicsabi64/atomicsabi64.rst#id30
@CarolineConcatto Yes, https://github.com/ARM-software/abi-aa/blob/main/atomicsabi64/atomicsabi64.rst#bit-floating-point-types shows what the instructions should be before and after. In PR #137703, you can see in the diffs that this changes to a single
and obviously fmin/fminimum are similar. |
50efa5b to
92ea098
Compare
|
Looks like something went wrong here? |
fc3d0e9 to
ef8e20b
Compare
A rebase fixed it; looks like it was transient. |
CarolineConcatto
approved these changes
Apr 30, 2025
…tructions (#136759) This patch adds support for LLVM IR atomicrmw `fmaximum` and `fminimum` instructions. These mirror the `llvm.maximum.*` and `llvm.minimum.*` instructions, but are atomic and use IEEE754 2019 handling for NaNs, which is different to `fmax` and `fmin`. See: https://llvm.org/docs/LangRef.html#llvm-minimum-intrinsic for more details. Future changes will allow this LLVM IR to be lowered to specialised assembler instructions on suitable targets, such as AArch64.
Add pre-commit tests for lowering atomicrmw `fminimum`/`fmaximum` to AArch64 assembler, in a subsequent change.
92ea098 to
5df3e4b
Compare
ef8e20b to
844142e
Compare
IanWood1
pushed a commit
to IanWood1/llvm-project
that referenced
this pull request
May 6, 2025
Add pre-commit tests for lowering atomicrmw `fminimum`/`fmaximum` to AArch64 assembler, in a subsequent change.
IanWood1
pushed a commit
to IanWood1/llvm-project
that referenced
this pull request
May 6, 2025
Add pre-commit tests for lowering atomicrmw `fminimum`/`fmaximum` to AArch64 assembler, in a subsequent change.
IanWood1
pushed a commit
to IanWood1/llvm-project
that referenced
this pull request
May 6, 2025
Add pre-commit tests for lowering atomicrmw `fminimum`/`fmaximum` to AArch64 assembler, in a subsequent change.
GeorgeARM
pushed a commit
to GeorgeARM/llvm-project
that referenced
this pull request
May 7, 2025
Add pre-commit tests for lowering atomicrmw `fminimum`/`fmaximum` to AArch64 assembler, in a subsequent change.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add pre-commit tests for lowering atomicrmw
fminimum/fmaximumto AArch64 assembler, in a subsequent change.