[llvm] [AMDGPU][GlobalISel] Add combines with or/and that only use half of 64bit values (PR #151519)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 31 06:35:37 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Mirko BrkuĊĦanin (mbrkusanin)
<details>
<summary>Changes</summary>
If we only deal with a one part of 64bit value we can just generate merge and
unmerge which will be either combined away or selected into copy / mov_b32.
---
Patch is 130.88 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/151519.diff
15 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/AMDGPUCombine.td (+19-2)
- (modified) llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.cpp (+26)
- (modified) llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.h (+5)
- (added) llvm/test/CodeGen/AMDGPU/GlobalISel/combine-and-or-s64-s32.mir (+175)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-phis-no-lane-mask-merging.ll (+13-16)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll (+41-51)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/fshr.ll (+450-476)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/sdiv.i64.ll (+4-6)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/sext_inreg.ll (+14-16)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/srem.i64.ll (+23-25)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/udiv.i64.ll (+4-6)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/urem.i64.ll (+4-6)
- (modified) llvm/test/CodeGen/AMDGPU/div_i128.ll (+24-24)
- (modified) llvm/test/CodeGen/AMDGPU/div_v2i128.ll (+32-32)
- (modified) llvm/test/CodeGen/AMDGPU/itofp.i128.ll (+8-8)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCombine.td b/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
index 9587fad1ecd63..97c3c8e9c10c8 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
@@ -151,6 +151,21 @@ def zext_of_shift_amount_combines : GICombineGroup<[
canonicalize_zext_lshr, canonicalize_zext_ashr, canonicalize_zext_shl
]>;
+// (or i64:x, (zext i32:y)) -> i64:(merge (or i32:y, lo_32(x)), hi_32(x))
+def combine_or_s64_s32 : GICombineRule<
+ (defs root:$dst),
+ (match (G_ZEXT $zext_val, i32:$src_s32):$zext_inst,
+ (G_OR $dst, i64:$src_s64, $zext_val):$dst),
+ (apply [{ Helper.applyCombineOrS64S32(*${dst}, ${src_s64}.getReg(), ${src_s32}.getReg()); }])>;
+
+// (and i64:x, 0xFFFFFFFF00000000) -> i64:(merge i32:0, hi_32(x))
+def combine_and_s64_himask : GICombineRule<
+ (defs root:$dst),
+ (match (G_CONSTANT $const, 0xFFFFFFFF00000000),
+ (G_AND $dst, i64:$src_s64, $const):$dst),
+ (apply [{ Helper.applyCombineAndS64HiMask(*${dst}, ${src_s64}.getReg()); }])>;
+
+
let Predicates = [Has16BitInsts, NotHasMed3_16] in {
// For gfx8, expand f16-fmed3-as-f32 into a min/max f16 sequence. This
// saves one instruction compared to the promotion.
@@ -180,7 +195,8 @@ def gfx8_combines : GICombineGroup<[expand_promoted_fmed3]>;
def AMDGPUPreLegalizerCombiner: GICombiner<
"AMDGPUPreLegalizerCombinerImpl",
[all_combines, combine_fmul_with_select_to_fldexp, clamp_i64_to_i16,
- foldable_fneg, combine_shuffle_vector_to_build_vector]> {
+ foldable_fneg, combine_shuffle_vector_to_build_vector,
+ combine_or_s64_s32, combine_and_s64_himask]> {
let CombineAllMethodName = "tryCombineAllImpl";
}
@@ -188,7 +204,8 @@ def AMDGPUPostLegalizerCombiner: GICombiner<
"AMDGPUPostLegalizerCombinerImpl",
[all_combines, gfx6gfx7_combines, gfx8_combines, combine_fmul_with_select_to_fldexp,
uchar_to_float, cvt_f32_ubyteN, remove_fcanonicalize, foldable_fneg,
- rcp_sqrt_to_rsq, fdiv_by_sqrt_to_rsq_f16, sign_extension_in_reg, smulu64]> {
+ rcp_sqrt_to_rsq, fdiv_by_sqrt_to_rsq_f16, sign_extension_in_reg, smulu64,
+ combine_or_s64_s32, combine_and_s64_himask]> {
let CombineAllMethodName = "tryCombineAllImpl";
}
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.cpp
index bcc19932fd938..57cce72a10708 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.cpp
@@ -516,3 +516,29 @@ bool AMDGPUCombinerHelper::matchCombineFmulWithSelectToFldexp(
return true;
}
+
+void AMDGPUCombinerHelper::applyCombineOrS64S32(MachineInstr &MI,
+ Register SrcS64,
+ Register SrcS32) const {
+ Register DstReg = MI.getOperand(0).getReg();
+
+ auto UnmergeParts = Builder.buildUnmerge(LLT::scalar(32), SrcS64);
+ Register SrcS64Lo = UnmergeParts.getReg(0);
+ Register SrcS64Hi = UnmergeParts.getReg(1);
+
+ auto Or = Builder.buildOr(LLT::scalar(32), SrcS32, SrcS64Lo).getReg(0);
+ Builder.buildMergeValues(DstReg, {Or, SrcS64Hi});
+ MI.eraseFromParent();
+}
+
+void AMDGPUCombinerHelper::applyCombineAndS64HiMask(MachineInstr &MI,
+ Register SrcS64) const {
+ Register DstReg = MI.getOperand(0).getReg();
+
+ auto UnmergeParts = Builder.buildUnmerge(LLT::scalar(32), SrcS64);
+ Register SrcS64Hi = UnmergeParts.getReg(1);
+
+ auto Const = Builder.buildConstant(LLT::scalar(32), 0).getReg(0);
+ Builder.buildMergeValues(DstReg, {Const, SrcS64Hi});
+ MI.eraseFromParent();
+}
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.h b/llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.h
index 96e0b12a168a6..4bb9622f09ca6 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCombinerHelper.h
@@ -43,6 +43,11 @@ class AMDGPUCombinerHelper : public CombinerHelper {
bool matchCombineFmulWithSelectToFldexp(
MachineInstr &MI, MachineInstr &Sel,
std::function<void(MachineIRBuilder &)> &MatchInfo) const;
+
+ void applyCombineOrS64S32(MachineInstr &MI, Register S64, Register S32) const;
+
+ void applyCombineAndS64HiMask(MachineInstr &MI, Register S64) const;
+
};
} // namespace llvm
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-and-or-s64-s32.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-and-or-s64-s32.mir
new file mode 100644
index 0000000000000..561d1a064d21d
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-and-or-s64-s32.mir
@@ -0,0 +1,175 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn -mcpu=tahiti -run-pass=amdgpu-prelegalizer-combiner %s -o - | FileCheck %s
+
+---
+name: test_combine_or_s64_s32
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0, $sgpr1, $sgpr2
+ ; CHECK-LABEL: name: test_combine_or_s64_s32
+ ; CHECK: liveins: $sgpr0, $sgpr1, $sgpr2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[COPY2]], [[COPY]]
+ ; CHECK-NEXT: $sgpr0 = COPY [[OR]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[COPY1]](s32)
+ ; CHECK-NEXT: SI_RETURN_TO_EPILOG implicit $sgpr0, implicit $sgpr1
+ %0:_(s32) = COPY $sgpr0
+ %1:_(s32) = COPY $sgpr1
+ %2:_(s32) = COPY $sgpr2
+ %3:_(s64) = G_MERGE_VALUES %0(s32), %1(s32)
+ %4:_(s64) = G_ZEXT %2(s32)
+ %5:_(s64) = disjoint G_OR %3, %4
+ %6:_(s32), %7:_(s32) = G_UNMERGE_VALUES %5(s64)
+ $sgpr0 = COPY %6(s32)
+ $sgpr1 = COPY %7(s32)
+ SI_RETURN_TO_EPILOG implicit $sgpr0, implicit $sgpr1
+...
+---
+name: test_combine_and_s64_himask
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0, $sgpr1, $sgpr2
+ ; CHECK-LABEL: name: test_combine_and_s64_himask
+ ; CHECK: liveins: $sgpr0, $sgpr1, $sgpr2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+ ; CHECK-NEXT: $sgpr0 = COPY [[C]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[COPY]](s32)
+ ; CHECK-NEXT: SI_RETURN_TO_EPILOG implicit $sgpr0, implicit $sgpr1
+ %0:_(s32) = COPY $sgpr0
+ %1:_(s32) = COPY $sgpr1
+ %2:_(s64) = G_MERGE_VALUES %0(s32), %1(s32)
+ %3:_(s64) = G_CONSTANT i64 -4294967296
+ %4:_(s64) = G_AND %2, %3
+ %5:_(s32), %6:_(s32) = G_UNMERGE_VALUES %4(s64)
+ $sgpr0 = COPY %5(s32)
+ $sgpr1 = COPY %6(s32)
+ SI_RETURN_TO_EPILOG implicit $sgpr0, implicit $sgpr1
+...
+---
+name: test_combined
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0, $sgpr1, $sgpr2
+ ; CHECK-LABEL: name: test_combined
+ ; CHECK: liveins: $sgpr0, $sgpr1, $sgpr2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: $sgpr0 = COPY [[COPY1]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[COPY]](s32)
+ ; CHECK-NEXT: SI_RETURN_TO_EPILOG implicit $sgpr0, implicit $sgpr1
+ %0:_(s32) = COPY $sgpr0
+ %1:_(s32) = COPY $sgpr1
+ %2:_(s32) = COPY $sgpr2
+ %3:_(s64) = G_MERGE_VALUES %0(s32), %1(s32)
+ %4:_(s64) = G_CONSTANT i64 -4294967296
+ %5:_(s64) = G_AND %3, %4
+ %6:_(s64) = G_ZEXT %2(s32)
+ %7:_(s64) = disjoint G_OR %5, %6
+ %8:_(s32), %9:_(s32) = G_UNMERGE_VALUES %7(s64)
+ $sgpr0 = COPY %8(s32)
+ $sgpr1 = COPY %9(s32)
+ SI_RETURN_TO_EPILOG implicit $sgpr0, implicit $sgpr1
+...
+
+---
+name: test_combine_or_s64_s32_no_merge_unmerge
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1, $sgpr2
+ ; CHECK-LABEL: name: test_combine_or_s64_s32_no_merge_unmerge
+ ; CHECK: liveins: $sgpr0_sgpr1, $sgpr2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $sgpr0_sgpr1
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
+ ; CHECK-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[COPY1]], [[UV]]
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[OR]](s32), [[UV1]](s32)
+ ; CHECK-NEXT: $sgpr0_sgpr1 = COPY [[MV]](s64)
+ ; CHECK-NEXT: SI_RETURN_TO_EPILOG implicit $sgpr0_sgpr1
+ %0:_(s64) = COPY $sgpr0_sgpr1
+ %1:_(s32) = COPY $sgpr2
+ %2:_(s64) = G_ZEXT %1(s32)
+ %3:_(s64) = disjoint G_OR %0, %2
+ $sgpr0_sgpr1 = COPY %3(s64)
+ SI_RETURN_TO_EPILOG implicit $sgpr0_sgpr1
+...
+---
+name: test_combine_and_s64_himask_no_merge_unmerge
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1, $sgpr2
+ ; CHECK-LABEL: name: test_combine_and_s64_himask_no_merge_unmerge
+ ; CHECK: liveins: $sgpr0_sgpr1, $sgpr2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $sgpr0_sgpr1
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
+ ; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[C]](s32), [[UV1]](s32)
+ ; CHECK-NEXT: $sgpr0_sgpr1 = COPY [[MV]](s64)
+ ; CHECK-NEXT: SI_RETURN_TO_EPILOG implicit $sgpr0_sgpr1
+ %0:_(s64) = COPY $sgpr0_sgpr1
+ %1:_(s64) = G_CONSTANT i64 -4294967296
+ %2:_(s64) = G_AND %0, %1
+ $sgpr0_sgpr1 = COPY %2(s64)
+ SI_RETURN_TO_EPILOG implicit $sgpr0_sgpr1
+...
+---
+name: test_combined_vgpr_no_merge_unmerge
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $vgpr0_vgpr1, $vgpr2
+
+ ; CHECK-LABEL: name: test_combined_vgpr
+ ; CHECK: liveins: $vgpr0_vgpr1, $vgpr2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr2
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY1]](s32), [[UV1]](s32)
+ ; CHECK-NEXT: $vgpr0_vgpr1 = COPY [[MV]](s64)
+ %1:_(s64) = COPY $vgpr0_vgpr1
+ %0:_(s32) = COPY $vgpr2
+ %2:_(s64) = G_CONSTANT i64 -4294967296
+ %3:_(s64) = G_AND %1, %2
+ %4:_(s64) = G_ZEXT %0
+ %5:_(s64) = G_OR %3, %4
+ $vgpr0_vgpr1 = COPY %5
+...
+---
+name: negative_test_incorrect_types
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5
+
+ ; CHECK-LABEL: name: negative_test_incorrect_types
+ ; CHECK: liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s128) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr4_vgpr5
+ ; CHECK-NEXT: [[C:%[0-9]+]]:_(s128) = G_CONSTANT i128 -4294967296
+ ; CHECK-NEXT: [[AND:%[0-9]+]]:_(s128) = G_AND [[COPY]], [[C]]
+ ; CHECK-NEXT: [[ZEXT:%[0-9]+]]:_(s128) = G_ZEXT [[COPY1]](s64)
+ ; CHECK-NEXT: [[OR:%[0-9]+]]:_(s128) = G_OR [[AND]], [[ZEXT]]
+ ; CHECK-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[OR]](s128)
+ %1:_(s128) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
+ %0:_(s64) = COPY $vgpr4_vgpr5
+ %2:_(s128) = G_CONSTANT i128 -4294967296
+ %3:_(s128) = G_AND %1, %2
+ %4:_(s128) = G_ZEXT %0
+ %5:_(s128) = G_OR %3, %4
+ $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %5
+...
+
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-phis-no-lane-mask-merging.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-phis-no-lane-mask-merging.ll
index ff26ea21390e2..667fa988d8f9c 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-phis-no-lane-mask-merging.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-phis-no-lane-mask-merging.ll
@@ -227,23 +227,20 @@ exit:
define amdgpu_cs void @single_lane_execution_attribute(i32 inreg %.userdata0, <3 x i32> inreg %.WorkgroupId, <3 x i32> %.LocalInvocationId) #0 {
; GFX10-LABEL: single_lane_execution_attribute:
; GFX10: ; %bb.0: ; %.entry
-; GFX10-NEXT: s_mov_b32 s6, 0
; GFX10-NEXT: s_getpc_b64 s[4:5]
-; GFX10-NEXT: s_mov_b32 s7, -1
-; GFX10-NEXT: s_mov_b32 s2, s1
-; GFX10-NEXT: s_and_b64 s[4:5], s[4:5], s[6:7]
-; GFX10-NEXT: s_mov_b32 s1, 0
+; GFX10-NEXT: s_mov_b32 s2, s0
+; GFX10-NEXT: s_mov_b32 s3, s5
; GFX10-NEXT: v_mbcnt_lo_u32_b32 v1, -1, 0
-; GFX10-NEXT: s_or_b64 s[12:13], s[4:5], s[0:1]
-; GFX10-NEXT: s_load_dwordx8 s[4:11], s[12:13], 0x0
+; GFX10-NEXT: s_load_dwordx8 s[4:11], s[2:3], 0x0
; GFX10-NEXT: v_mbcnt_hi_u32_b32 v1, -1, v1
; GFX10-NEXT: v_lshlrev_b32_e32 v2, 2, v1
; GFX10-NEXT: v_and_b32_e32 v3, 1, v1
; GFX10-NEXT: v_cmp_ne_u32_e32 vcc_lo, 0, v3
-; GFX10-NEXT: s_xor_b32 s3, vcc_lo, exec_lo
+; GFX10-NEXT: s_xor_b32 s2, vcc_lo, exec_lo
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-NEXT: buffer_load_dword v2, v2, s[4:7], 0 offen
-; GFX10-NEXT: s_and_b32 vcc_lo, exec_lo, s3
+; GFX10-NEXT: s_and_b32 vcc_lo, exec_lo, s2
+; GFX10-NEXT: s_mov_b32 s2, 0
; GFX10-NEXT: s_waitcnt vmcnt(0)
; GFX10-NEXT: v_cmp_eq_u32_e64 s0, 0, v2
; GFX10-NEXT: s_cbranch_vccnz .LBB4_4
@@ -251,9 +248,9 @@ define amdgpu_cs void @single_lane_execution_attribute(i32 inreg %.userdata0, <3
; GFX10-NEXT: s_mov_b32 s3, 0
; GFX10-NEXT: .LBB4_2: ; %.preheader
; GFX10-NEXT: ; =>This Inner Loop Header: Depth=1
-; GFX10-NEXT: v_mov_b32_e32 v3, s1
+; GFX10-NEXT: v_mov_b32_e32 v3, s2
; GFX10-NEXT: v_add_nc_u32_e32 v1, -1, v1
-; GFX10-NEXT: s_add_i32 s1, s1, 4
+; GFX10-NEXT: s_add_i32 s2, s2, 4
; GFX10-NEXT: buffer_load_dword v3, v3, s[4:7], 0 offen
; GFX10-NEXT: v_cmp_ne_u32_e32 vcc_lo, 0, v1
; GFX10-NEXT: s_waitcnt vmcnt(0)
@@ -262,19 +259,19 @@ define amdgpu_cs void @single_lane_execution_attribute(i32 inreg %.userdata0, <3
; GFX10-NEXT: s_cbranch_vccnz .LBB4_2
; GFX10-NEXT: ; %bb.3: ; %.preheader._crit_edge
; GFX10-NEXT: v_cmp_eq_u32_e32 vcc_lo, s3, v2
-; GFX10-NEXT: s_or_b32 s1, s0, vcc_lo
-; GFX10-NEXT: v_cndmask_b32_e64 v1, 0, 1, s1
+; GFX10-NEXT: s_or_b32 s2, s0, vcc_lo
+; GFX10-NEXT: v_cndmask_b32_e64 v1, 0, 1, s2
; GFX10-NEXT: s_branch .LBB4_6
; GFX10-NEXT: .LBB4_4:
-; GFX10-NEXT: s_mov_b32 s1, exec_lo
+; GFX10-NEXT: s_mov_b32 s2, exec_lo
; GFX10-NEXT: ; implicit-def: $vgpr1
-; GFX10-NEXT: s_and_b32 vcc_lo, exec_lo, s1
+; GFX10-NEXT: s_and_b32 vcc_lo, exec_lo, s2
; GFX10-NEXT: s_cbranch_vccz .LBB4_6
; GFX10-NEXT: ; %bb.5: ; %.19
; GFX10-NEXT: v_cndmask_b32_e64 v1, 0, 1, s0
; GFX10-NEXT: v_or_b32_e32 v1, 2, v1
; GFX10-NEXT: .LBB4_6: ; %.22
-; GFX10-NEXT: v_add_lshl_u32 v0, v0, s2, 2
+; GFX10-NEXT: v_add_lshl_u32 v0, v0, s1, 2
; GFX10-NEXT: buffer_store_dword v1, v0, s[8:11], 0 offen
; GFX10-NEXT: s_endpgm
.entry:
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll
index fc81e16d68e98..dd61428811736 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll
@@ -4959,17 +4959,15 @@ define amdgpu_ps i64 @s_fshl_i64_5(i64 inreg %lhs, i64 inreg %rhs) {
; GCN: ; %bb.0:
; GCN-NEXT: s_lshl_b64 s[0:1], s[0:1], 5
; GCN-NEXT: s_lshr_b32 s2, s3, 27
-; GCN-NEXT: s_mov_b32 s3, 0
-; GCN-NEXT: s_or_b64 s[0:1], s[0:1], s[2:3]
+; GCN-NEXT: s_or_b32 s0, s2, s0
; GCN-NEXT: ; return to shader part epilog
;
; GFX11-LABEL: s_fshl_i64_5:
; GFX11: ; %bb.0:
; GFX11-NEXT: s_lshl_b64 s[0:1], s[0:1], 5
; GFX11-NEXT: s_lshr_b32 s2, s3, 27
-; GFX11-NEXT: s_mov_b32 s3, 0
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
-; GFX11-NEXT: s_or_b64 s[0:1], s[0:1], s[2:3]
+; GFX11-NEXT: s_or_b32 s0, s2, s0
; GFX11-NEXT: ; return to shader part epilog
%result = call i64 @llvm.fshl.i64(i64 %lhs, i64 %rhs, i64 5)
ret i64 %result
@@ -4979,20 +4977,13 @@ define amdgpu_ps i64 @s_fshl_i64_32(i64 inreg %lhs, i64 inreg %rhs) {
; GCN-LABEL: s_fshl_i64_32:
; GCN: ; %bb.0:
; GCN-NEXT: s_mov_b32 s1, s0
-; GCN-NEXT: s_mov_b32 s0, 0
-; GCN-NEXT: s_mov_b32 s2, s3
-; GCN-NEXT: s_mov_b32 s3, s0
-; GCN-NEXT: s_or_b64 s[0:1], s[0:1], s[2:3]
+; GCN-NEXT: s_mov_b32 s0, s3
; GCN-NEXT: ; return to shader part epilog
;
; GFX11-LABEL: s_fshl_i64_32:
; GFX11: ; %bb.0:
; GFX11-NEXT: s_mov_b32 s1, s0
-; GFX11-NEXT: s_mov_b32 s0, 0
-; GFX11-NEXT: s_mov_b32 s2, s3
-; GFX11-NEXT: s_mov_b32 s3, s0
-; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
-; GFX11-NEXT: s_or_b64 s[0:1], s[0:1], s[2:3]
+; GFX11-NEXT: s_mov_b32 s0, s3
; GFX11-NEXT: ; return to shader part epilog
%result = call i64 @llvm.fshl.i64(i64 %lhs, i64 %rhs, i64 32)
ret i64 %result
@@ -5097,7 +5088,7 @@ define i64 @v_fshl_i64_5(i64 %lhs, i64 %rhs) {
; GFX6-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX6-NEXT: v_lshl_b64 v[0:1], v[0:1], 5
; GFX6-NEXT: v_lshrrev_b32_e32 v2, 27, v3
-; GFX6-NEXT: v_or_b32_e32 v0, v0, v2
+; GFX6-NEXT: v_or_b32_e32 v0, v2, v0
; GFX6-NEXT: s_setpc_b64 s[30:31]
;
; GFX8-LABEL: v_fshl_i64_5:
@@ -5105,7 +5096,7 @@ define i64 @v_fshl_i64_5(i64 %lhs, i64 %rhs) {
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX8-NEXT: v_lshlrev_b64 v[0:1], 5, v[0:1]
; GFX8-NEXT: v_lshrrev_b32_e32 v2, 27, v3
-; GFX8-NEXT: v_or_b32_e32 v0, v0, v2
+; GFX8-NEXT: v_or_b32_e32 v0, v2, v0
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: v_fshl_i64_5:
@@ -5113,7 +5104,7 @@ define i64 @v_fshl_i64_5(i64 %lhs, i64 %rhs) {
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_lshlrev_b64 v[0:1], 5, v[0:1]
; GFX9-NEXT: v_lshrrev_b32_e32 v2, 27, v3
-; GFX9-NEXT: v_or_b32_e32 v0, v0, v2
+; GFX9-NEXT: v_or_b32_e32 v0, v2, v0
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_fshl_i64_5:
@@ -5121,7 +5112,7 @@ define i64 @v_fshl_i64_5(i64 %lhs, i64 %rhs) {
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT: v_lshlrev_b64 v[0:1], 5, v[0:1]
; GFX10-NEXT: v_lshrrev_b32_e32 v2, 27, v3
-; GFX10-NEXT: v_or_b32_e32 v0, v0, v2
+; GFX10-NEXT: v_or_b32_e32 v0, v2, v0
; GFX10-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: v_fshl_i64_5:
@@ -5130,7 +5121,7 @@ define i64 @v_fshl_i64_5(i64 %lhs, i64 %rhs) {
; GFX11-NEXT: v_lshlrev_b64 v[0:1], 5, v[0:1]
; GFX11-NEXT: v_lshrrev_b32_e32 v2, 27, v3
; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
-; GFX11-NEXT: v_or_b32_e32 v0, v0, v2
+; GFX11-NEXT: v_or_b32_e32 v0, v2, v0
; GFX11-NEXT: s_setpc_b64 s[30:31]
%result = call i64 @llvm.fshl.i64(i64 %lhs, i64 %rhs, i64 5)
ret i64 %result
@@ -6876,57 +6867,56 @@ define amdgpu_ps i128 @s_fshl_i128_65(i128 inreg %lhs, i128 inreg %rhs) {
; GFX6-LABEL: s_fshl_i128_65:
; GFX6: ; %bb.0:
; GFX6-NEXT: s_lshl_b64 s[2:3], s[0:1], 1
-; GFX6-NEXT: s_lshr_b32 s4, s5, 31
-; GFX6-NEXT: s_mov_b32 s5, 0
-; GFX6-NEXT: s_lshl_b64 s[0:1], s[6:7], 1
-; GFX6-NEXT: s_or_b64 s[0:1], s[4:5], s[0:1]
+; GFX6-NEXT: s_lshr_b32 s0, s5, 31
+; GFX6-NEXT: s_mov_b32 s1, 0
+; GFX6-NEXT: s_lshl_b64 s[4:5], s[6:7], 1
+; GFX6-NEXT: s_or_b64 s[0:1], s[0:1], s[4:5]
; GFX6-NEXT: s_lshr_b32 s4, s7, 31
-; GFX6-NEXT: s_or_b64 s[2:3], s[2:3], s[4:5]
+; GFX6-NEXT: s_or_b32 s2, s4, s2
; GFX6-NEXT: ; return to shader part epilog
;
; GFX8-LABEL: s_fshl_i128_65:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_lshl_b64 s[2:3], s[0:1], 1
-; GFX8-NEXT: s_lshr_b32 s4, s5, 31
-; GFX8-NEXT: s_mov_b32 s5, 0
-; GFX8-NEXT: s_lshl_b64 s[0:1], s[6:7], 1
-; GFX8-NEXT: s_or_b64 s[0:1], s[4:5], s[0:1]
+; GFX8-NEXT: s_lshr_b32 s0, s5, 31
+; GFX8-NEXT: s_mov_b32 s1, 0
+; GFX8-NEXT: s_lshl_b64 s[4:5], s[6:7], 1
+; GFX8-NEXT: s_or_b64 s[0:1], s[0:1], s[4:5]
; GFX8-NEXT: s_lshr_b32 s4, s7, 31
-; GFX8-NEXT: s_or_b64 s[2:3], s[2:3], s[4:5]
+; GFX8-NEXT: s_or_b32 s2, s4, s2
; GFX8-NEXT: ; return to shader part epilog
;
; GFX9-LABEL: s_fshl_i128_65:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_lshl_b64 s[2:3], s[0:1], 1
-; GFX9-NEXT: s_lshr_b32 s4, s5, 31
-; GFX9-NEXT: s_mov_b32 s5, 0
-; GFX9-NEXT: s_lshl_b64 s[0:1], s[6:7], 1
-; GFX9-NEXT: s_or_b64 s[0:1], s[4:5], s[0:1]
+; GFX9-NEXT: s_lshr_b32 s0, s5, 31
+; GFX9-NEXT: s_mov_b32 s1, 0
+; GFX9-NEXT: s_lshl_b64 s[4:5], s[6:7], 1
+;...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/151519
More information about the llvm-commits
mailing list