[llvm] [AMDGPU] Ignore inactive VGPRs in .vgpr_count (PR #149052)
Diana Picus via llvm-commits
llvm-commits at lists.llvm.org
Mon Aug 11 01:53:42 PDT 2025
https://github.com/rovka updated https://github.com/llvm/llvm-project/pull/149052
>From 3ad0c0e5fa98b35c3176ee0f917eb962671e5ab8 Mon Sep 17 00:00:00 2001
From: Diana Picus <diana-magda.picus at amd.com>
Date: Wed, 16 Jul 2025 09:34:09 +0200
Subject: [PATCH] [AMDGPU] Ignore inactive VGPRs in .vgpr_count
When using the `amdgcn.init.whole.wave` intrinsic, we add dummy VGPR
arguments with the purpose of preserving their inactive lanes. The
pattern may look something like this:
```
entry:
call amdgcn.init.whole.wave
branch to shader or tail
shader:
$vInactive = IMPLICIT_DEF ; Tells regalloc it's safe to use the active lanes
actual code...
tail:
call amdgcn.cs.chain [...], implicit $vInactive
```
We should not report these VGPRs in the `.vgpr_count` metadata. This patch
achieves that goal by ignoring IMPLICIT_DEFs and calls. This should be
safe since if those registers are actually used in any other context,
they will be counted there. The same reasoning applies in the general
case, so we don't explicitly check for the existence of
`init.whole.wave`.
This is a reworked version of #133242, which was reverted in #144039 and
split into smaller patches.
---
.../AMDGPU/AMDGPUResourceUsageAnalysis.cpp | 3 +
.../init-whole-wave-vgpr-count-large.ll | 76 ++++++++++++++++++
.../AMDGPU/init-whole-wave-vgpr-count-leaf.ll | 50 ++++++++++++
...init-whole-wave-vgpr-count-use-inactive.ll | 78 +++++++++++++++++++
.../AMDGPU/init-whole-wave-vgpr-count.ll | 75 ++++++++++++++++++
.../AMDGPU/unnamed-function-resource-info.ll | 2 +-
.../CodeGen/AMDGPU/vgpr-agpr-limit-gfx90a.ll | 4 +-
.../test/CodeGen/AMDGPU/vgpr-count-compute.ll | 30 +++++++
.../AMDGPU/vgpr-count-graphics-chain.ll | 26 +++++++
.../CodeGen/AMDGPU/vgpr-count-graphics.ll | 24 ++++++
10 files changed, 365 insertions(+), 3 deletions(-)
create mode 100644 llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-large.ll
create mode 100644 llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-leaf.ll
create mode 100644 llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-use-inactive.ll
create mode 100644 llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count.ll
create mode 100644 llvm/test/CodeGen/AMDGPU/vgpr-count-compute.ll
create mode 100644 llvm/test/CodeGen/AMDGPU/vgpr-count-graphics-chain.ll
create mode 100644 llvm/test/CodeGen/AMDGPU/vgpr-count-graphics.ll
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
index 8101c68986241..84d1ce8ee8a8b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
@@ -241,6 +241,9 @@ AMDGPUResourceUsageAnalysisImpl::analyzeResourceUsage(
if (!RC || !TRI.isVGPRClass(RC))
continue;
+ if (MI.isCall() || MI.isImplicitDef())
+ continue;
+
unsigned Width = divideCeil(TRI.getRegSizeInBits(*RC), 32);
unsigned HWReg = TRI.getHWRegIndex(Reg);
int MaxUsed = HWReg + Width - 1;
diff --git a/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-large.ll b/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-large.ll
new file mode 100644
index 0000000000000..340447b53c5c7
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-large.ll
@@ -0,0 +1,76 @@
+; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1200 < %s | FileCheck %s
+
+; CHECK-LABEL: .shader_functions:
+
+; Use VGPRs above the input arguments.
+; CHECK-LABEL: _miss_1:
+; CHECK: .vgpr_count: 0x1d{{$}}
+
+define amdgpu_cs_chain void @_miss_1(ptr inreg %next.callee, i32 inreg %global.table, i32 inreg %max.outgoing.vgpr.count,
+ i32 %vcr, { i32 } %system.data,
+ i32 %inactive.vgpr, i32 %inactive.vgpr1, i32 %inactive.vgpr2, i32 %inactive.vgpr3,
+ i32 %inactive.vgpr4, i32 %inactive.vgpr5, i32 %inactive.vgpr6, i32 %inactive.vgpr7,
+ i32 %inactive.vgpr8, i32 %inactive.vgpr9)
+ local_unnamed_addr {
+entry:
+ %system.data.value = extractvalue { i32 } %system.data, 0
+ %dead.val = call i32 @llvm.amdgcn.dead.i32()
+ %is.whole.wave = call i1 @llvm.amdgcn.init.whole.wave()
+ br i1 %is.whole.wave, label %shader, label %tail
+
+shader:
+ %system.data.extract = extractvalue { i32 } %system.data, 0
+ %data.mul = mul i32 %system.data.extract, 2
+ %data.add = add i32 %data.mul, 1
+ call void asm sideeffect "; clobber v28", "~{v28}"()
+ br label %tail
+
+tail:
+ %final.vcr = phi i32 [ %vcr, %entry ], [ %data.mul, %shader ]
+ %final.sys.data = phi i32 [ %system.data.value, %entry ], [ %data.add, %shader ]
+ %final.inactive0 = phi i32 [ %inactive.vgpr, %entry ], [ %dead.val, %shader ]
+ %final.inactive1 = phi i32 [ %inactive.vgpr1, %entry ], [ %dead.val, %shader ]
+ %final.inactive2 = phi i32 [ %inactive.vgpr2, %entry ], [ %dead.val, %shader ]
+ %final.inactive3 = phi i32 [ %inactive.vgpr3, %entry ], [ %dead.val, %shader ]
+ %final.inactive4 = phi i32 [ %inactive.vgpr4, %entry ], [ %dead.val, %shader ]
+ %final.inactive5 = phi i32 [ %inactive.vgpr5, %entry ], [ %dead.val, %shader ]
+ %final.inactive6 = phi i32 [ %inactive.vgpr6, %entry ], [ %dead.val, %shader ]
+ %final.inactive7 = phi i32 [ %inactive.vgpr7, %entry ], [ %dead.val, %shader ]
+ %final.inactive8 = phi i32 [ %inactive.vgpr8, %entry ], [ %dead.val, %shader ]
+ %final.inactive9 = phi i32 [ %inactive.vgpr9, %entry ], [ %dead.val, %shader ]
+
+ %struct.init = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } poison, i32 %final.vcr, 0
+ %struct.with.data = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.init, i32 %final.sys.data, 1
+ %struct.with.inactive0 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.data, i32 %final.inactive0, 2
+ %struct.with.inactive1 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive0, i32 %final.inactive1, 3
+ %struct.with.inactive2 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive1, i32 %final.inactive2, 4
+ %struct.with.inactive3 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive2, i32 %final.inactive3, 5
+ %struct.with.inactive4 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive3, i32 %final.inactive4, 6
+ %struct.with.inactive5 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive4, i32 %final.inactive5, 7
+ %struct.with.inactive6 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive5, i32 %final.inactive6, 8
+ %struct.with.inactive7 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive6, i32 %final.inactive7, 9
+ %struct.with.inactive8 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive7, i32 %final.inactive8, 10
+ %final.struct = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive8, i32 %final.inactive9, 11
+
+ %vec.global = insertelement <4 x i32> poison, i32 %global.table, i64 0
+ %vec.max.vgpr = insertelement <4 x i32> %vec.global, i32 %max.outgoing.vgpr.count, i64 1
+ %vec.sys.data = insertelement <4 x i32> %vec.max.vgpr, i32 %final.sys.data, i64 2
+ %final.vec = insertelement <4 x i32> %vec.sys.data, i32 0, i64 3
+
+ call void (ptr, i32, <4 x i32>, { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 }, i32, ...)
+ @llvm.amdgcn.cs.chain.p0.i32.v4i32.sl_i32i32i32i32i32i32i32i32i32i32i32i32s(
+ ptr %next.callee, i32 0, <4 x i32> inreg %final.vec,
+ { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %final.struct,
+ i32 1, i32 %max.outgoing.vgpr.count, i32 -1, ptr @retry_vgpr_alloc.v4i32)
+ unreachable
+}
+
+declare i32 @llvm.amdgcn.dead.i32()
+declare i1 @llvm.amdgcn.init.whole.wave()
+declare void @llvm.amdgcn.cs.chain.p0.i32.v4i32.sl_i32i32i32i32i32i32i32i32i32i32i32i32s(ptr, i32, <4 x i32>, { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 }, i32 immarg, ...)
+
+declare amdgpu_cs_chain void @retry_vgpr_alloc.v4i32(<4 x i32> inreg)
+
+!amdgpu.pal.metadata.msgpack = !{!0}
+
+!0 = !{!"\82\B0amdpal.pipelines\91\8B\A4.api\A6Vulkan\B2.compute_registers\85\AB.tg_size_en\C3\AA.tgid_x_en\C3\AA.tgid_y_en\C3\AA.tgid_z_en\C3\AF.tidig_comp_cnt\00\B0.hardware_stages\81\A3.cs\8D\AF.checksum_value\00\AB.debug_mode\00\AB.float_mode\CC\C0\A9.image_op\C2\AC.mem_ordered\C3\AB.sgpr_limitj\B7.threadgroup_dimensions\93 \01\01\AD.trap_present\00\B2.user_data_reg_map\90\AB.user_sgprs\10\AB.vgpr_limit\CD\01\00\AF.wavefront_size \AF.wg_round_robin\C2\B7.internal_pipeline_hash\92\CF|{2&\DCC\85M\CFep\8A\EDR\DE\D6\E1\B1.shader_functions\81\A7_miss_1\82\B4.frontend_stack_size\00\B4.outgoing_vgpr_countP\A8.shaders\81\A8.compute\82\B0.api_shader_hash\92\00\00\B1.hardware_mapping\91\A3.cs\B0.spill_threshold\CD\FF\FF\A5.type\A2Cs\B0.user_data_limit\01\A9.uses_cps\C3\AF.xgl_cache_info\82\B3.128_bit_cache_hash\92\CF\B4\AF\9D\0B\07\88\03\02\CF\01o\C9\CAf?)\DA\AD.llpc_version\A476.0\AEamdpal.version\92\03\00"}
diff --git a/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-leaf.ll b/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-leaf.ll
new file mode 100644
index 0000000000000..ca506b618b8ed
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-leaf.ll
@@ -0,0 +1,50 @@
+; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1200 < %s | FileCheck %s
+
+; CHECK-LABEL: .shader_functions:
+
+; Make sure that .vgpr_count doesn't include the %inactive.vgpr registers.
+; CHECK-LABEL: leaf_shader:
+; CHECK: .vgpr_count: 0xc{{$}}
+
+; Function without calls.
+define amdgpu_cs_chain void @_leaf_shader(ptr %output.ptr, i32 inreg %input.value,
+ i32 %active.vgpr1, i32 %active.vgpr2,
+ i32 %inactive.vgpr1, i32 %inactive.vgpr2, i32 %inactive.vgpr3,
+ i32 %inactive.vgpr4, i32 %inactive.vgpr5, i32 %inactive.vgpr6)
+ local_unnamed_addr {
+entry:
+ %dead.val = call i32 @llvm.amdgcn.dead.i32()
+ %is.whole.wave = call i1 @llvm.amdgcn.init.whole.wave()
+ br i1 %is.whole.wave, label %compute, label %merge
+
+compute:
+ ; Perform a more complex computation using active VGPRs
+ %square = mul i32 %active.vgpr1, %active.vgpr1
+ %product = mul i32 %square, %active.vgpr2
+ %sum = add i32 %product, %input.value
+ %result = add i32 %sum, 42
+ br label %merge
+
+merge:
+ %final.result = phi i32 [ 0, %entry ], [ %result, %compute ]
+ %final.inactive1 = phi i32 [ %inactive.vgpr1, %entry ], [ %dead.val, %compute ]
+ %final.inactive2 = phi i32 [ %inactive.vgpr2, %entry ], [ %dead.val, %compute ]
+ %final.inactive3 = phi i32 [ %inactive.vgpr3, %entry ], [ %dead.val, %compute ]
+ %final.inactive4 = phi i32 [ %inactive.vgpr4, %entry ], [ %dead.val, %compute ]
+ %final.inactive5 = phi i32 [ %inactive.vgpr5, %entry ], [ %dead.val, %compute ]
+ %final.inactive6 = phi i32 [ %inactive.vgpr6, %entry ], [ %dead.val, %compute ]
+
+ store i32 %final.result, ptr %output.ptr, align 4
+
+ ret void
+}
+
+declare i32 @llvm.amdgcn.dead.i32()
+declare i1 @llvm.amdgcn.init.whole.wave()
+declare void @llvm.amdgcn.cs.chain.p0.i32.v4i32.sl_i32i32i32i32i32i32i32i32i32i32i32i32s(ptr, i32, <4 x i32>, { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 }, i32 immarg, ...)
+
+declare amdgpu_cs_chain void @retry_vgpr_alloc.v4i32(<4 x i32> inreg)
+
+!amdgpu.pal.metadata.msgpack = !{!0}
+
+!0 = !{!"\82\B0amdpal.pipelines\91\8B\A4.api\A6Vulkan\B2.compute_registers\85\AB.tg_size_en\C3\AA.tgid_x_en\C3\AA.tgid_y_en\C3\AA.tgid_z_en\C3\AF.tidig_comp_cnt\00\B0.hardware_stages\81\A3.cs\8D\AF.checksum_value\00\AB.debug_mode\00\AB.float_mode\CC\C0\A9.image_op\C2\AC.mem_ordered\C3\AB.sgpr_limitj\B7.threadgroup_dimensions\93 \01\01\AD.trap_present\00\B2.user_data_reg_map\90\AB.user_sgprs\10\AB.vgpr_limit\CD\01\00\AF.wavefront_size \AF.wg_round_robin\C2\B7.internal_pipeline_hash\92\CF|{2&\DCC\85M\CFep\8A\EDR\DE\D6\E1\B1.shader_functions\81\A7_miss_1\82\B4.frontend_stack_size\00\B4.outgoing_vgpr_countP\A8.shaders\81\A8.compute\82\B0.api_shader_hash\92\00\00\B1.hardware_mapping\91\A3.cs\B0.spill_threshold\CD\FF\FF\A5.type\A2Cs\B0.user_data_limit\01\A9.uses_cps\C3\AF.xgl_cache_info\82\B3.128_bit_cache_hash\92\CF\B4\AF\9D\0B\07\88\03\02\CF\01o\C9\CAf?)\DA\AD.llpc_version\A476.0\AEamdpal.version\92\03\00"}
diff --git a/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-use-inactive.ll b/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-use-inactive.ll
new file mode 100644
index 0000000000000..fec0d5dc61a13
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count-use-inactive.ll
@@ -0,0 +1,78 @@
+; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1200 < %s | FileCheck %s
+
+; CHECK-LABEL: .shader_functions:
+
+; Make sure that .vgpr_count doesn't include the %inactive.vgpr registers.
+; The shader is free to use any of the VGPRs mapped to a %inactive.vgpr as long as it only touches its active lanes.
+; In that case, the VGPR should be included in the .vgpr_count
+; CHECK-LABEL: _miss_1:
+; CHECK: .vgpr_count: 0xd{{$}}
+
+define amdgpu_cs_chain void @_miss_1(ptr inreg %next.callee, i32 inreg %global.table, i32 inreg %max.outgoing.vgpr.count,
+ i32 %vcr, { i32 } %system.data,
+ i32 %inactive.vgpr, i32 %inactive.vgpr1, i32 %inactive.vgpr2, i32 %inactive.vgpr3,
+ i32 %inactive.vgpr4, i32 %inactive.vgpr5, i32 %inactive.vgpr6, i32 %inactive.vgpr7,
+ i32 %inactive.vgpr8, i32 %inactive.vgpr9)
+ local_unnamed_addr {
+entry:
+ %system.data.value = extractvalue { i32 } %system.data, 0
+ %dead.val = call i32 @llvm.amdgcn.dead.i32()
+ %is.whole.wave = call i1 @llvm.amdgcn.init.whole.wave()
+ br i1 %is.whole.wave, label %shader, label %tail
+
+shader:
+ %system.data.extract = extractvalue { i32 } %system.data, 0
+ %data.mul = mul i32 %system.data.extract, 2
+ %data.add = add i32 %data.mul, 1
+ call void asm sideeffect "; clobber VGPR for %inactive.vgpr2", "~{v12}"()
+ br label %tail
+
+tail:
+ %final.vcr = phi i32 [ %vcr, %entry ], [ %data.mul, %shader ]
+ %final.sys.data = phi i32 [ %system.data.value, %entry ], [ %data.add, %shader ]
+ %final.inactive0 = phi i32 [ %inactive.vgpr, %entry ], [ %dead.val, %shader ]
+ %final.inactive1 = phi i32 [ %inactive.vgpr1, %entry ], [ %dead.val, %shader ]
+ %final.inactive2 = phi i32 [ %inactive.vgpr2, %entry ], [ %dead.val, %shader ]
+ %final.inactive3 = phi i32 [ %inactive.vgpr3, %entry ], [ %dead.val, %shader ]
+ %final.inactive4 = phi i32 [ %inactive.vgpr4, %entry ], [ %dead.val, %shader ]
+ %final.inactive5 = phi i32 [ %inactive.vgpr5, %entry ], [ %dead.val, %shader ]
+ %final.inactive6 = phi i32 [ %inactive.vgpr6, %entry ], [ %dead.val, %shader ]
+ %final.inactive7 = phi i32 [ %inactive.vgpr7, %entry ], [ %dead.val, %shader ]
+ %final.inactive8 = phi i32 [ %inactive.vgpr8, %entry ], [ %dead.val, %shader ]
+ %final.inactive9 = phi i32 [ %inactive.vgpr9, %entry ], [ %dead.val, %shader ]
+
+ %struct.init = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } poison, i32 %final.vcr, 0
+ %struct.with.data = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.init, i32 %final.sys.data, 1
+ %struct.with.inactive0 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.data, i32 %final.inactive0, 2
+ %struct.with.inactive1 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive0, i32 %final.inactive1, 3
+ %struct.with.inactive2 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive1, i32 %final.inactive2, 4
+ %struct.with.inactive3 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive2, i32 %final.inactive3, 5
+ %struct.with.inactive4 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive3, i32 %final.inactive4, 6
+ %struct.with.inactive5 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive4, i32 %final.inactive5, 7
+ %struct.with.inactive6 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive5, i32 %final.inactive6, 8
+ %struct.with.inactive7 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive6, i32 %final.inactive7, 9
+ %struct.with.inactive8 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive7, i32 %final.inactive8, 10
+ %final.struct = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive8, i32 %final.inactive9, 11
+
+ %vec.global = insertelement <4 x i32> poison, i32 %global.table, i64 0
+ %vec.max.vgpr = insertelement <4 x i32> %vec.global, i32 %max.outgoing.vgpr.count, i64 1
+ %vec.sys.data = insertelement <4 x i32> %vec.max.vgpr, i32 %final.sys.data, i64 2
+ %final.vec = insertelement <4 x i32> %vec.sys.data, i32 0, i64 3
+
+ call void (ptr, i32, <4 x i32>, { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 }, i32, ...)
+ @llvm.amdgcn.cs.chain.p0.i32.v4i32.sl_i32i32i32i32i32i32i32i32i32i32i32i32s(
+ ptr %next.callee, i32 0, <4 x i32> inreg %final.vec,
+ { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %final.struct,
+ i32 1, i32 %max.outgoing.vgpr.count, i32 -1, ptr @retry_vgpr_alloc.v4i32)
+ unreachable
+}
+
+declare i32 @llvm.amdgcn.dead.i32()
+declare i1 @llvm.amdgcn.init.whole.wave()
+declare void @llvm.amdgcn.cs.chain.p0.i32.v4i32.sl_i32i32i32i32i32i32i32i32i32i32i32i32s(ptr, i32, <4 x i32>, { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 }, i32 immarg, ...)
+
+declare amdgpu_cs_chain void @retry_vgpr_alloc.v4i32(<4 x i32> inreg)
+
+!amdgpu.pal.metadata.msgpack = !{!0}
+
+!0 = !{!"\82\B0amdpal.pipelines\91\8B\A4.api\A6Vulkan\B2.compute_registers\85\AB.tg_size_en\C3\AA.tgid_x_en\C3\AA.tgid_y_en\C3\AA.tgid_z_en\C3\AF.tidig_comp_cnt\00\B0.hardware_stages\81\A3.cs\8D\AF.checksum_value\00\AB.debug_mode\00\AB.float_mode\CC\C0\A9.image_op\C2\AC.mem_ordered\C3\AB.sgpr_limitj\B7.threadgroup_dimensions\93 \01\01\AD.trap_present\00\B2.user_data_reg_map\90\AB.user_sgprs\10\AB.vgpr_limit\CD\01\00\AF.wavefront_size \AF.wg_round_robin\C2\B7.internal_pipeline_hash\92\CF|{2&\DCC\85M\CFep\8A\EDR\DE\D6\E1\B1.shader_functions\81\A7_miss_1\82\B4.frontend_stack_size\00\B4.outgoing_vgpr_countP\A8.shaders\81\A8.compute\82\B0.api_shader_hash\92\00\00\B1.hardware_mapping\91\A3.cs\B0.spill_threshold\CD\FF\FF\A5.type\A2Cs\B0.user_data_limit\01\A9.uses_cps\C3\AF.xgl_cache_info\82\B3.128_bit_cache_hash\92\CF\B4\AF\9D\0B\07\88\03\02\CF\01o\C9\CAf?)\DA\AD.llpc_version\A476.0\AEamdpal.version\92\03\00"}
diff --git a/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count.ll b/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count.ll
new file mode 100644
index 0000000000000..c4c51ca513e86
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/init-whole-wave-vgpr-count.ll
@@ -0,0 +1,75 @@
+; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1200 < %s | FileCheck %s
+
+; CHECK-LABEL: .shader_functions:
+
+; Make sure that .vgpr_count doesn't include the %inactive.vgpr registers.
+; CHECK-LABEL: _miss_1:
+; CHECK: .vgpr_count: 0xa{{$}}
+
+define amdgpu_cs_chain void @_miss_1(ptr inreg %next.callee, i32 inreg %global.table, i32 inreg %max.outgoing.vgpr.count,
+ i32 %vcr, { i32 } %system.data,
+ i32 %inactive.vgpr, i32 %inactive.vgpr1, i32 %inactive.vgpr2, i32 %inactive.vgpr3,
+ i32 %inactive.vgpr4, i32 %inactive.vgpr5, i32 %inactive.vgpr6, i32 %inactive.vgpr7,
+ i32 %inactive.vgpr8, i32 %inactive.vgpr9)
+ local_unnamed_addr {
+entry:
+ %system.data.value = extractvalue { i32 } %system.data, 0
+ %dead.val = call i32 @llvm.amdgcn.dead.i32()
+ %is.whole.wave = call i1 @llvm.amdgcn.init.whole.wave()
+ br i1 %is.whole.wave, label %shader, label %tail
+
+shader:
+ %system.data.extract = extractvalue { i32 } %system.data, 0
+ %data.mul = mul i32 %system.data.extract, 2
+ %data.add = add i32 %data.mul, 1
+ br label %tail
+
+tail:
+ %final.vcr = phi i32 [ %vcr, %entry ], [ %data.mul, %shader ]
+ %final.sys.data = phi i32 [ %system.data.value, %entry ], [ %data.add, %shader ]
+ %final.inactive0 = phi i32 [ %inactive.vgpr, %entry ], [ %dead.val, %shader ]
+ %final.inactive1 = phi i32 [ %inactive.vgpr1, %entry ], [ %dead.val, %shader ]
+ %final.inactive2 = phi i32 [ %inactive.vgpr2, %entry ], [ %dead.val, %shader ]
+ %final.inactive3 = phi i32 [ %inactive.vgpr3, %entry ], [ %dead.val, %shader ]
+ %final.inactive4 = phi i32 [ %inactive.vgpr4, %entry ], [ %dead.val, %shader ]
+ %final.inactive5 = phi i32 [ %inactive.vgpr5, %entry ], [ %dead.val, %shader ]
+ %final.inactive6 = phi i32 [ %inactive.vgpr6, %entry ], [ %dead.val, %shader ]
+ %final.inactive7 = phi i32 [ %inactive.vgpr7, %entry ], [ %dead.val, %shader ]
+ %final.inactive8 = phi i32 [ %inactive.vgpr8, %entry ], [ %dead.val, %shader ]
+ %final.inactive9 = phi i32 [ %inactive.vgpr9, %entry ], [ %dead.val, %shader ]
+
+ %struct.init = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } poison, i32 %final.vcr, 0
+ %struct.with.data = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.init, i32 %final.sys.data, 1
+ %struct.with.inactive0 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.data, i32 %final.inactive0, 2
+ %struct.with.inactive1 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive0, i32 %final.inactive1, 3
+ %struct.with.inactive2 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive1, i32 %final.inactive2, 4
+ %struct.with.inactive3 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive2, i32 %final.inactive3, 5
+ %struct.with.inactive4 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive3, i32 %final.inactive4, 6
+ %struct.with.inactive5 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive4, i32 %final.inactive5, 7
+ %struct.with.inactive6 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive5, i32 %final.inactive6, 8
+ %struct.with.inactive7 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive6, i32 %final.inactive7, 9
+ %struct.with.inactive8 = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive7, i32 %final.inactive8, 10
+ %final.struct = insertvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %struct.with.inactive8, i32 %final.inactive9, 11
+
+ %vec.global = insertelement <4 x i32> poison, i32 %global.table, i64 0
+ %vec.max.vgpr = insertelement <4 x i32> %vec.global, i32 %max.outgoing.vgpr.count, i64 1
+ %vec.sys.data = insertelement <4 x i32> %vec.max.vgpr, i32 %final.sys.data, i64 2
+ %final.vec = insertelement <4 x i32> %vec.sys.data, i32 0, i64 3
+
+ call void (ptr, i32, <4 x i32>, { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 }, i32, ...)
+ @llvm.amdgcn.cs.chain.p0.i32.v4i32.sl_i32i32i32i32i32i32i32i32i32i32i32i32s(
+ ptr %next.callee, i32 0, <4 x i32> inreg %final.vec,
+ { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %final.struct,
+ i32 1, i32 %max.outgoing.vgpr.count, i32 -1, ptr @retry_vgpr_alloc.v4i32)
+ unreachable
+}
+
+declare i32 @llvm.amdgcn.dead.i32()
+declare i1 @llvm.amdgcn.init.whole.wave()
+declare void @llvm.amdgcn.cs.chain.p0.i32.v4i32.sl_i32i32i32i32i32i32i32i32i32i32i32i32s(ptr, i32, <4 x i32>, { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 }, i32 immarg, ...)
+
+declare amdgpu_cs_chain void @retry_vgpr_alloc.v4i32(<4 x i32> inreg)
+
+!amdgpu.pal.metadata.msgpack = !{!0}
+
+!0 = !{!"\82\B0amdpal.pipelines\91\8B\A4.api\A6Vulkan\B2.compute_registers\85\AB.tg_size_en\C3\AA.tgid_x_en\C3\AA.tgid_y_en\C3\AA.tgid_z_en\C3\AF.tidig_comp_cnt\00\B0.hardware_stages\81\A3.cs\8D\AF.checksum_value\00\AB.debug_mode\00\AB.float_mode\CC\C0\A9.image_op\C2\AC.mem_ordered\C3\AB.sgpr_limitj\B7.threadgroup_dimensions\93 \01\01\AD.trap_present\00\B2.user_data_reg_map\90\AB.user_sgprs\10\AB.vgpr_limit\CD\01\00\AF.wavefront_size \AF.wg_round_robin\C2\B7.internal_pipeline_hash\92\CF|{2&\DCC\85M\CFep\8A\EDR\DE\D6\E1\B1.shader_functions\81\A7_miss_1\82\B4.frontend_stack_size\00\B4.outgoing_vgpr_countP\A8.shaders\81\A8.compute\82\B0.api_shader_hash\92\00\00\B1.hardware_mapping\91\A3.cs\B0.spill_threshold\CD\FF\FF\A5.type\A2Cs\B0.user_data_limit\01\A9.uses_cps\C3\AF.xgl_cache_info\82\B3.128_bit_cache_hash\92\CF\B4\AF\9D\0B\07\88\03\02\CF\01o\C9\CAf?)\DA\AD.llpc_version\A476.0\AEamdpal.version\92\03\00"}
diff --git a/llvm/test/CodeGen/AMDGPU/unnamed-function-resource-info.ll b/llvm/test/CodeGen/AMDGPU/unnamed-function-resource-info.ll
index cf5b95a729974..bb0ec0d3ad3f8 100644
--- a/llvm/test/CodeGen/AMDGPU/unnamed-function-resource-info.ll
+++ b/llvm/test/CodeGen/AMDGPU/unnamed-function-resource-info.ll
@@ -16,7 +16,7 @@ entry:
}
; CHECK-LABEL: __unnamed_2:
-; CHECK: .set __unnamed_2.num_vgpr, max(32, __unnamed_1.num_vgpr)
+; CHECK: .set __unnamed_2.num_vgpr, max(1, __unnamed_1.num_vgpr)
; CHECK: .set __unnamed_2.num_agpr, max(0, __unnamed_1.num_agpr)
; CHECK: .set __unnamed_2.numbered_sgpr, max(34, __unnamed_1.numbered_sgpr)
; CHECK: .set __unnamed_2.private_seg_size, 16+max(__unnamed_1.private_seg_size)
diff --git a/llvm/test/CodeGen/AMDGPU/vgpr-agpr-limit-gfx90a.ll b/llvm/test/CodeGen/AMDGPU/vgpr-agpr-limit-gfx90a.ll
index 2cb5e309c8c21..ee35dc4cddade 100644
--- a/llvm/test/CodeGen/AMDGPU/vgpr-agpr-limit-gfx90a.ll
+++ b/llvm/test/CodeGen/AMDGPU/vgpr-agpr-limit-gfx90a.ll
@@ -1264,9 +1264,9 @@ define amdgpu_kernel void @k1024_call_no_agprs_ub_callee() #1025 {
}
; GCN-LABEL: {{^}}f1024_0:
-; GFX90A: NumVgprs: 32
+; GFX90A: NumVgprs: 1
; GFX90A: NumAgprs: 1
-; GFX90A: TotalNumVgprs: 33
+; GFX90A: TotalNumVgprs: 5
define void @f1024_0() #1024 {
call void @foo()
ret void
diff --git a/llvm/test/CodeGen/AMDGPU/vgpr-count-compute.ll b/llvm/test/CodeGen/AMDGPU/vgpr-count-compute.ll
new file mode 100644
index 0000000000000..71d4e6b277320
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/vgpr-count-compute.ll
@@ -0,0 +1,30 @@
+; RUN: llc -mcpu=gfx1200 < %s | FileCheck %s --check-prefixes=CHECK,PACKED
+; RUN: llc -mcpu=gfx1030 < %s | FileCheck %s --check-prefixes=CHECK,NOTPACKED
+target triple = "amdgcn-amd-amdhsa"
+
+ at global = addrspace(1) global i32 poison, align 4
+
+; Carefully crafted kernel that uses v0 but never writes a VGPR or reads another VGPR.
+; Only hardware-initialized VGPRs (v0) are read in this kernel.
+
+; CHECK-LABEL: amdhsa.kernels:
+; CHECK-LABEL: kernel_x
+; CHECK: .vgpr_count: 1
+define amdgpu_kernel void @kernel_x(ptr addrspace(8) %rsrc) #0 {
+entry:
+ %id = call i32 @llvm.amdgcn.workitem.id.x()
+ call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %id, ptr addrspace(8) %rsrc, i32 0, i32 0, i32 0)
+ ret void
+}
+
+; CHECK-LABEL: kernel_z
+; PACKED: .vgpr_count: 1
+; NOTPACKED: .vgpr_count: 3
+define amdgpu_kernel void @kernel_z(ptr addrspace(8) %rsrc) {
+entry:
+ %id = call i32 @llvm.amdgcn.workitem.id.z()
+ call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %id, ptr addrspace(8) %rsrc, i32 0, i32 0, i32 0)
+ ret void
+}
+
+attributes #0 = { "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" }
diff --git a/llvm/test/CodeGen/AMDGPU/vgpr-count-graphics-chain.ll b/llvm/test/CodeGen/AMDGPU/vgpr-count-graphics-chain.ll
new file mode 100644
index 0000000000000..a9f4bda12c557
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/vgpr-count-graphics-chain.ll
@@ -0,0 +1,26 @@
+; RUN: llc -mcpu=gfx1200 < %s | FileCheck %s
+target triple = "amdgcn--amdpal"
+
+ at global = addrspace(1) global i32 poison, align 4
+
+; CHECK-LABEL: amdpal.pipelines:
+
+; Shouldn't report the part of %vgpr_args that's not used
+; CHECK-LABEL: entry_point_symbol: cs_calling_chain
+; CHECK: .vgpr_count: 0xa
+define amdgpu_cs void @cs_calling_chain(i32 %vgpr, i32 inreg %sgpr) {
+ %vgpr_args = insertvalue {i32, i32, i32, i32} poison, i32 %vgpr, 1
+ call void (ptr, i32, i32, {i32, i32, i32, i32}, i32, ...) @llvm.amdgcn.cs.chain.p0.i32.i32.s(
+ ptr @chain_func, i32 0, i32 inreg %sgpr, {i32, i32, i32, i32} %vgpr_args, i32 0)
+ unreachable
+}
+
+; Neither uses not writes a VGPR
+; CHECK-LABEL: chain_func:
+; CHECK: .vgpr_count: 0x1
+define amdgpu_cs_chain void @chain_func([32 x i32] %args) {
+entry:
+ call void (ptr, i32, {}, [32 x i32], i32, ...) @llvm.amdgcn.cs.chain.p0.i32.s.a(
+ ptr @chain_func, i32 0, {} inreg {}, [32 x i32] %args, i32 0)
+ unreachable
+}
diff --git a/llvm/test/CodeGen/AMDGPU/vgpr-count-graphics.ll b/llvm/test/CodeGen/AMDGPU/vgpr-count-graphics.ll
new file mode 100644
index 0000000000000..ea19763d61f41
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/vgpr-count-graphics.ll
@@ -0,0 +1,24 @@
+; RUN: llc -mcpu=gfx1200 < %s | FileCheck %s
+target triple = "amdgcn--amdpal"
+
+ at global = addrspace(1) global i32 poison, align 4
+
+; CHECK-LABEL: amdpal.pipelines:
+
+; Neither uses not writes a VGPR, but the hardware initializes the VGPRs that the kernel receives, so they count as used.
+; CHECK-LABEL: .entry_point_symbol: kernel_use
+; CHECK: .vgpr_count: 0x20
+define amdgpu_cs void @kernel_use([32 x i32] %args) {
+entry:
+ %a = extractvalue [32 x i32] %args, 14
+ store i32 %a, ptr addrspace(1) @global
+ ret void
+}
+
+; Neither uses not writes a VGPR
+; CHECK-LABEL: gfx_func:
+; CHECK: .vgpr_count: 0x20
+define amdgpu_gfx [32 x i32] @gfx_func([32 x i32] %args) {
+entry:
+ ret [32 x i32] %args
+}
More information about the llvm-commits
mailing list