[NFC][AMDGPU] Pre-commit test for setcc removal by using add/sub carryout #155118
+186
−0
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
Signed-off-by: John Lu <John.Lu@amd.com>
|
@llvm/pr-subscribers-backend-amdgpu Author: None (LU-JOHN) ChangesPre-commit test for setcc removal by using add/sub carryout. Full diff: https://github.com/llvm/llvm-project/pull/155118.diff 1 Files Affected:
diff --git a/llvm/test/CodeGen/AMDGPU/addsub64_carry.ll b/llvm/test/CodeGen/AMDGPU/addsub64_carry.ll
new file mode 100644
index 0000000000000..5cdb0b2407bbc
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/addsub64_carry.ll
@@ -0,0 +1,186 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+;; Test that carryout from 64-bit add/sub (synthesized from two 32-bit adds/subs) is utilized
+;; (i.e. no additional compare is generated).
+
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck %s
+
+%0 = type { i64, i64, i32, i32 }
+%1 = type { [64 x [8 x i64]] }
+%struct.uint96 = type { i64, i32 }
+%struct.uint64pair = type { i64, i64 }
+
+declare {i64, i1} @llvm.uadd.with.overflow.i64(i64, i64)
+declare {i64, i1} @llvm.usub.with.overflow.i64(i64, i64)
+
+declare {<2 x i64>, <2 x i1>} @llvm.uadd.with.overflow.v2i64(<2 x i64>, <2 x i64>)
+declare {<2 x i64>, <2 x i1>} @llvm.usub.with.overflow.v2i64(<2 x i64>, <2 x i64>)
+
+define hidden %struct.uint96 @add64_32(i64 %val64A, i64 %val64B, i32 %val32) {
+; CHECK-LABEL: add64_32:
+; CHECK: ; %bb.0:
+; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT: v_add_co_u32_e32 v5, vcc, v0, v2
+; CHECK-NEXT: v_addc_co_u32_e32 v6, vcc, v1, v3, vcc
+; CHECK-NEXT: v_cmp_lt_u64_e32 vcc, v[5:6], v[0:1]
+; CHECK-NEXT: v_mov_b32_e32 v0, v5
+; CHECK-NEXT: v_addc_co_u32_e32 v2, vcc, 0, v4, vcc
+; CHECK-NEXT: v_mov_b32_e32 v1, v6
+; CHECK-NEXT: s_setpc_b64 s[30:31]
+ %sum64 = add i64 %val64A, %val64B
+ %obit = icmp ult i64 %sum64, %val64A
+ %obit32 = zext i1 %obit to i32
+ %sum32 = add i32 %val32, %obit32
+ %.fca.0.insert = insertvalue %struct.uint96 poison, i64 %sum64, 0
+ %.fca.1.insert = insertvalue %struct.uint96 %.fca.0.insert, i32 %sum32, 1
+ ret %struct.uint96 %.fca.1.insert
+}
+
+define <2 x i64> @uadd_v2i64(<2 x i64> %val0, <2 x i64> %val1, ptr %ptrval) {
+; CHECK-LABEL: uadd_v2i64:
+; CHECK: ; %bb.0:
+; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT: v_add_co_u32_e32 v6, vcc, v2, v6
+; CHECK-NEXT: v_addc_co_u32_e32 v7, vcc, v3, v7, vcc
+; CHECK-NEXT: v_add_co_u32_e32 v4, vcc, v0, v4
+; CHECK-NEXT: v_addc_co_u32_e32 v5, vcc, v1, v5, vcc
+; CHECK-NEXT: v_cmp_lt_u64_e32 vcc, v[4:5], v[0:1]
+; CHECK-NEXT: flat_store_dwordx4 v[8:9], v[4:7]
+; CHECK-NEXT: v_cndmask_b32_e64 v0, 0, -1, vcc
+; CHECK-NEXT: v_cmp_lt_u64_e32 vcc, v[6:7], v[2:3]
+; CHECK-NEXT: v_mov_b32_e32 v1, v0
+; CHECK-NEXT: v_cndmask_b32_e64 v2, 0, -1, vcc
+; CHECK-NEXT: v_mov_b32_e32 v3, v2
+; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; CHECK-NEXT: s_setpc_b64 s[30:31]
+ %pair = call {<2 x i64>, <2 x i1>} @llvm.uadd.with.overflow.v2i64(<2 x i64> %val0, <2 x i64> %val1)
+ %val = extractvalue {<2 x i64>, <2 x i1>} %pair, 0
+ %obit = extractvalue {<2 x i64>, <2 x i1>} %pair, 1
+ %res = sext <2 x i1> %obit to <2 x i64>
+ store <2 x i64> %val, ptr %ptrval
+ ret <2 x i64> %res
+}
+
+define <2 x i64> @usub_v2i64(<2 x i64> %val0, <2 x i64> %val1, ptr %ptrval) {
+; CHECK-LABEL: usub_v2i64:
+; CHECK: ; %bb.0:
+; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT: v_sub_co_u32_e32 v6, vcc, v2, v6
+; CHECK-NEXT: v_subb_co_u32_e32 v7, vcc, v3, v7, vcc
+; CHECK-NEXT: v_sub_co_u32_e32 v4, vcc, v0, v4
+; CHECK-NEXT: v_subb_co_u32_e32 v5, vcc, v1, v5, vcc
+; CHECK-NEXT: v_cmp_gt_u64_e32 vcc, v[4:5], v[0:1]
+; CHECK-NEXT: flat_store_dwordx4 v[8:9], v[4:7]
+; CHECK-NEXT: v_cndmask_b32_e64 v0, 0, -1, vcc
+; CHECK-NEXT: v_cmp_gt_u64_e32 vcc, v[6:7], v[2:3]
+; CHECK-NEXT: v_mov_b32_e32 v1, v0
+; CHECK-NEXT: v_cndmask_b32_e64 v2, 0, -1, vcc
+; CHECK-NEXT: v_mov_b32_e32 v3, v2
+; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; CHECK-NEXT: s_setpc_b64 s[30:31]
+ %pair = call {<2 x i64>, <2 x i1>} @llvm.usub.with.overflow.v2i64(<2 x i64> %val0, <2 x i64> %val1)
+ %val = extractvalue {<2 x i64>, <2 x i1>} %pair, 0
+ %obit = extractvalue {<2 x i64>, <2 x i1>} %pair, 1
+ %res = sext <2 x i1> %obit to <2 x i64>
+ store <2 x i64> %val, ptr %ptrval
+ ret <2 x i64> %res
+}
+
+define i64 @uadd_i64(i64 %val0, i64 %val1, ptr %ptrval) {
+; CHECK-LABEL: uadd_i64:
+; CHECK: ; %bb.0:
+; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT: v_add_co_u32_e32 v2, vcc, v0, v2
+; CHECK-NEXT: v_addc_co_u32_e32 v3, vcc, v1, v3, vcc
+; CHECK-NEXT: v_cmp_lt_u64_e32 vcc, v[2:3], v[0:1]
+; CHECK-NEXT: flat_store_dwordx2 v[4:5], v[2:3]
+; CHECK-NEXT: v_cndmask_b32_e64 v0, 0, -1, vcc
+; CHECK-NEXT: v_mov_b32_e32 v1, v0
+; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; CHECK-NEXT: s_setpc_b64 s[30:31]
+ %pair = call {i64, i1} @llvm.uadd.with.overflow.i64(i64 %val0, i64 %val1)
+ %val = extractvalue {i64, i1} %pair, 0
+ %obit = extractvalue {i64, i1} %pair, 1
+ %res = sext i1 %obit to i64
+ store i64 %val, ptr %ptrval
+ ret i64 %res
+}
+
+define i64 @uadd_p1(i64 %val0, i64 %val1, ptr %ptrval) {
+; CHECK-LABEL: uadd_p1:
+; CHECK: ; %bb.0:
+; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT: v_add_co_u32_e32 v0, vcc, 1, v0
+; CHECK-NEXT: v_addc_co_u32_e32 v1, vcc, 0, v1, vcc
+; CHECK-NEXT: v_cmp_eq_u64_e32 vcc, 0, v[0:1]
+; CHECK-NEXT: flat_store_dwordx2 v[4:5], v[0:1]
+; CHECK-NEXT: v_cndmask_b32_e64 v0, 0, -1, vcc
+; CHECK-NEXT: v_mov_b32_e32 v1, v0
+; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; CHECK-NEXT: s_setpc_b64 s[30:31]
+ %pair = call {i64, i1} @llvm.uadd.with.overflow.i64(i64 %val0, i64 1)
+ %val = extractvalue {i64, i1} %pair, 0
+ %obit = extractvalue {i64, i1} %pair, 1
+ %res = sext i1 %obit to i64
+ store i64 %val, ptr %ptrval
+ ret i64 %res
+}
+
+define i64 @uadd_n1(i64 %val0, i64 %val1, ptr %ptrval) {
+; CHECK-LABEL: uadd_n1:
+; CHECK: ; %bb.0:
+; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT: v_add_co_u32_e32 v2, vcc, -1, v0
+; CHECK-NEXT: v_addc_co_u32_e32 v3, vcc, -1, v1, vcc
+; CHECK-NEXT: v_cmp_ne_u64_e32 vcc, 0, v[0:1]
+; CHECK-NEXT: flat_store_dwordx2 v[4:5], v[2:3]
+; CHECK-NEXT: v_cndmask_b32_e64 v0, 0, -1, vcc
+; CHECK-NEXT: v_mov_b32_e32 v1, v0
+; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; CHECK-NEXT: s_setpc_b64 s[30:31]
+ %pair = call {i64, i1} @llvm.uadd.with.overflow.i64(i64 %val0, i64 -1)
+ %val = extractvalue {i64, i1} %pair, 0
+ %obit = extractvalue {i64, i1} %pair, 1
+ %res = sext i1 %obit to i64
+ store i64 %val, ptr %ptrval
+ ret i64 %res
+}
+
+define i64 @usub_p1(i64 %val0, i64 %val1, ptr %ptrval) {
+; CHECK-LABEL: usub_p1:
+; CHECK: ; %bb.0:
+; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT: v_add_co_u32_e32 v2, vcc, -1, v0
+; CHECK-NEXT: v_addc_co_u32_e32 v3, vcc, -1, v1, vcc
+; CHECK-NEXT: v_cmp_gt_u64_e32 vcc, v[2:3], v[0:1]
+; CHECK-NEXT: flat_store_dwordx2 v[4:5], v[2:3]
+; CHECK-NEXT: v_cndmask_b32_e64 v0, 0, -1, vcc
+; CHECK-NEXT: v_mov_b32_e32 v1, v0
+; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; CHECK-NEXT: s_setpc_b64 s[30:31]
+ %pair = call {i64, i1} @llvm.usub.with.overflow.i64(i64 %val0, i64 1)
+ %val = extractvalue {i64, i1} %pair, 0
+ %obit = extractvalue {i64, i1} %pair, 1
+ %res = sext i1 %obit to i64
+ store i64 %val, ptr %ptrval
+ ret i64 %res
+}
+
+define i64 @usub_n1(i64 %val0, i64 %val1, ptr %ptrval) {
+; CHECK-LABEL: usub_n1:
+; CHECK: ; %bb.0:
+; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT: v_add_co_u32_e32 v2, vcc, 1, v0
+; CHECK-NEXT: v_addc_co_u32_e32 v3, vcc, 0, v1, vcc
+; CHECK-NEXT: v_cmp_gt_u64_e32 vcc, v[2:3], v[0:1]
+; CHECK-NEXT: flat_store_dwordx2 v[4:5], v[2:3]
+; CHECK-NEXT: v_cndmask_b32_e64 v0, 0, -1, vcc
+; CHECK-NEXT: v_mov_b32_e32 v1, v0
+; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; CHECK-NEXT: s_setpc_b64 s[30:31]
+ %pair = call {i64, i1} @llvm.usub.with.overflow.i64(i64 %val0, i64 -1)
+ %val = extractvalue {i64, i1} %pair, 0
+ %obit = extractvalue {i64, i1} %pair, 1
+ %res = sext i1 %obit to i64
+ store i64 %val, ptr %ptrval
+ ret i64 %res
+}
|
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.
Pre-commit test for setcc removal by using add/sub carryout.