[llvm] AMDGPU/GlobalISel: Do not try to form v_bitop3_b32 for SGPR results (PR #117940)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Nov 27 15:33:47 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
<details>
<summary>Changes</summary>
This is a quick fix for expensive checks failures. These regressions
should be fixed with smarter regbankselect.
---
Full diff: https://github.com/llvm/llvm-project/pull/117940.diff
2 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp (+7-5)
- (modified) llvm/test/CodeGen/AMDGPU/bitop3.ll (+114-46)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
index 71d23f9fe30c49..3be865f03df1fd 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
@@ -3764,10 +3764,15 @@ bool AMDGPUInstructionSelector::selectBITOP3(MachineInstr &MI) const {
if (!Subtarget->hasBitOp3Insts())
return false;
+ Register DstReg = MI.getOperand(0).getReg();
+ const RegisterBank *DstRB = RBI.getRegBank(DstReg, *MRI, TRI);
+ const bool IsVALU = DstRB->getID() == AMDGPU::VGPRRegBankID;
+ if (!IsVALU)
+ return false;
+
SmallVector<Register, 3> Src;
uint8_t TTbl;
unsigned NumOpcodes;
- Register DstReg = MI.getOperand(0).getReg();
std::tie(NumOpcodes, TTbl) = BitOp3_Op(DstReg, Src, *MRI);
@@ -3776,13 +3781,10 @@ bool AMDGPUInstructionSelector::selectBITOP3(MachineInstr &MI) const {
if (NumOpcodes < 2 || Src.empty())
return false;
- const RegisterBank *DstRB = RBI.getRegBank(DstReg, *MRI, TRI);
- const bool IsVALU = DstRB->getID() == AMDGPU::VGPRRegBankID;
-
// For a uniform case threshold should be higher to account for moves between
// VGPRs and SGPRs. It needs one operand in a VGPR, rest two can be in SGPRs
// and a readtfirstlane after.
- if (NumOpcodes < 4 && !IsVALU)
+ if (NumOpcodes < 4)
return false;
bool IsB32 = MRI->getType(DstReg) == LLT::scalar(32);
diff --git a/llvm/test/CodeGen/AMDGPU/bitop3.ll b/llvm/test/CodeGen/AMDGPU/bitop3.ll
index dd608ef0e5a53d..b08ab5a2dc4223 100644
--- a/llvm/test/CodeGen/AMDGPU/bitop3.ll
+++ b/llvm/test/CodeGen/AMDGPU/bitop3.ll
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -march=amdgcn -mcpu=gfx950 < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX950,GFX950-SDAG %s
-; RUN: llc -global-isel -march=amdgcn -mcpu=gfx950 < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX950,GFX950-GISEL %s
+; RUN: llc -global-isel=0 -mtriple=amdgcn-- -mcpu=gfx950 < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX950,GFX950-SDAG %s
+; RUN: llc -global-isel -mtriple=amdgcn-- -mcpu=gfx950 < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX950,GFX950-GISEL %s
; ========= Single bit functions =========
@@ -45,10 +45,17 @@ define amdgpu_ps float @not_and_and_not_and(i32 %a, i32 %b, i32 %c) {
}
define amdgpu_ps float @not_and_and_and(i32 %a, i32 %b, i32 %c) {
-; GCN-LABEL: not_and_and_and:
-; GCN: ; %bb.0:
-; GCN-NEXT: v_bitop3_b32 v0, v0, v1, v2 bitop3:8
-; GCN-NEXT: ; return to shader part epilog
+; GFX950-SDAG-LABEL: not_and_and_and:
+; GFX950-SDAG: ; %bb.0:
+; GFX950-SDAG-NEXT: v_bitop3_b32 v0, v0, v1, v2 bitop3:8
+; GFX950-SDAG-NEXT: ; return to shader part epilog
+;
+; GFX950-GISEL-LABEL: not_and_and_and:
+; GFX950-GISEL: ; %bb.0:
+; GFX950-GISEL-NEXT: v_not_b32_e32 v0, v0
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v2
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v1
+; GFX950-GISEL-NEXT: ; return to shader part epilog
%nota = xor i32 %a, -1
%and1 = and i32 %nota, %c
%and2 = and i32 %and1, %b
@@ -70,10 +77,17 @@ define amdgpu_ps float @and_not_and_not_and(i32 %a, i32 %b, i32 %c) {
}
define amdgpu_ps float @and_not_and_and(i32 %a, i32 %b, i32 %c) {
-; GCN-LABEL: and_not_and_and:
-; GCN: ; %bb.0:
-; GCN-NEXT: v_bitop3_b32 v0, v0, v1, v2 bitop3:0x20
-; GCN-NEXT: ; return to shader part epilog
+; GFX950-SDAG-LABEL: and_not_and_and:
+; GFX950-SDAG: ; %bb.0:
+; GFX950-SDAG-NEXT: v_bitop3_b32 v0, v0, v1, v2 bitop3:0x20
+; GFX950-SDAG-NEXT: ; return to shader part epilog
+;
+; GFX950-GISEL-LABEL: and_not_and_and:
+; GFX950-GISEL: ; %bb.0:
+; GFX950-GISEL-NEXT: v_not_b32_e32 v1, v1
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v2
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v1
+; GFX950-GISEL-NEXT: ; return to shader part epilog
%notb = xor i32 %b, -1
%and1 = and i32 %a, %c
%and2 = and i32 %and1, %notb
@@ -82,10 +96,17 @@ define amdgpu_ps float @and_not_and_and(i32 %a, i32 %b, i32 %c) {
}
define amdgpu_ps float @and_and_not_and(i32 %a, i32 %b, i32 %c) {
-; GCN-LABEL: and_and_not_and:
-; GCN: ; %bb.0:
-; GCN-NEXT: v_bitop3_b32 v0, v0, v1, v2 bitop3:0x40
-; GCN-NEXT: ; return to shader part epilog
+; GFX950-SDAG-LABEL: and_and_not_and:
+; GFX950-SDAG: ; %bb.0:
+; GFX950-SDAG-NEXT: v_bitop3_b32 v0, v0, v1, v2 bitop3:0x40
+; GFX950-SDAG-NEXT: ; return to shader part epilog
+;
+; GFX950-GISEL-LABEL: and_and_not_and:
+; GFX950-GISEL: ; %bb.0:
+; GFX950-GISEL-NEXT: v_not_b32_e32 v2, v2
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v2
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v1
+; GFX950-GISEL-NEXT: ; return to shader part epilog
%notc = xor i32 %c, -1
%and1 = and i32 %a, %notc
%and2 = and i32 %and1, %b
@@ -94,10 +115,16 @@ define amdgpu_ps float @and_and_not_and(i32 %a, i32 %b, i32 %c) {
}
define amdgpu_ps float @and_and_and(i32 %a, i32 %b, i32 %c) {
-; GCN-LABEL: and_and_and:
-; GCN: ; %bb.0:
-; GCN-NEXT: v_bitop3_b32 v0, v0, v1, v2 bitop3:0x80
-; GCN-NEXT: ; return to shader part epilog
+; GFX950-SDAG-LABEL: and_and_and:
+; GFX950-SDAG: ; %bb.0:
+; GFX950-SDAG-NEXT: v_bitop3_b32 v0, v0, v1, v2 bitop3:0x80
+; GFX950-SDAG-NEXT: ; return to shader part epilog
+;
+; GFX950-GISEL-LABEL: and_and_and:
+; GFX950-GISEL: ; %bb.0:
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v2
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v1
+; GFX950-GISEL-NEXT: ; return to shader part epilog
%and1 = and i32 %a, %c
%and2 = and i32 %and1, %b
%ret_cast = bitcast i32 %and2 to float
@@ -107,10 +134,16 @@ define amdgpu_ps float @and_and_and(i32 %a, i32 %b, i32 %c) {
; ========= Multi bit functions =========
define amdgpu_ps float @test_12(i32 %a, i32 %b) {
-; GCN-LABEL: test_12:
-; GCN: ; %bb.0:
-; GCN-NEXT: v_bitop3_b32 v0, v0, v1, v0 bitop3:0xc
-; GCN-NEXT: ; return to shader part epilog
+; GFX950-SDAG-LABEL: test_12:
+; GFX950-SDAG: ; %bb.0:
+; GFX950-SDAG-NEXT: v_bitop3_b32 v0, v0, v1, v0 bitop3:0xc
+; GFX950-SDAG-NEXT: ; return to shader part epilog
+;
+; GFX950-GISEL-LABEL: test_12:
+; GFX950-GISEL: ; %bb.0:
+; GFX950-GISEL-NEXT: v_not_b32_e32 v0, v0
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v1
+; GFX950-GISEL-NEXT: ; return to shader part epilog
%nota = xor i32 %a, -1
%and1 = and i32 %nota, %b
%ret_cast = bitcast i32 %and1 to float
@@ -118,10 +151,17 @@ define amdgpu_ps float @test_12(i32 %a, i32 %b) {
}
define amdgpu_ps float @test_63(i32 %a, i32 %b) {
-; GCN-LABEL: test_63:
-; GCN: ; %bb.0:
-; GCN-NEXT: v_bitop3_b32 v0, v0, v1, v0 bitop3:0x3f
-; GCN-NEXT: ; return to shader part epilog
+; GFX950-SDAG-LABEL: test_63:
+; GFX950-SDAG: ; %bb.0:
+; GFX950-SDAG-NEXT: v_bitop3_b32 v0, v0, v1, v0 bitop3:0x3f
+; GFX950-SDAG-NEXT: ; return to shader part epilog
+;
+; GFX950-GISEL-LABEL: test_63:
+; GFX950-GISEL: ; %bb.0:
+; GFX950-GISEL-NEXT: v_not_b32_e32 v0, v0
+; GFX950-GISEL-NEXT: v_not_b32_e32 v1, v1
+; GFX950-GISEL-NEXT: v_or_b32_e32 v0, v0, v1
+; GFX950-GISEL-NEXT: ; return to shader part epilog
%nota = xor i32 %a, -1
%notb = xor i32 %b, -1
%or = or i32 %nota, %notb
@@ -143,10 +183,17 @@ define amdgpu_ps float @test_59(i32 %a, i32 %b, i32 %c) {
}
define amdgpu_ps float @test_126(i32 %a, i32 %b, i32 %c) {
-; GCN-LABEL: test_126:
-; GCN: ; %bb.0:
-; GCN-NEXT: v_bitop3_b32 v0, v0, v2, v1 bitop3:0x7e
-; GCN-NEXT: ; return to shader part epilog
+; GFX950-SDAG-LABEL: test_126:
+; GFX950-SDAG: ; %bb.0:
+; GFX950-SDAG-NEXT: v_bitop3_b32 v0, v0, v2, v1 bitop3:0x7e
+; GFX950-SDAG-NEXT: ; return to shader part epilog
+;
+; GFX950-GISEL-LABEL: test_126:
+; GFX950-GISEL: ; %bb.0:
+; GFX950-GISEL-NEXT: v_xor_b32_e32 v1, v0, v1
+; GFX950-GISEL-NEXT: v_xor_b32_e32 v0, v0, v2
+; GFX950-GISEL-NEXT: v_or_b32_e32 v0, v1, v0
+; GFX950-GISEL-NEXT: ; return to shader part epilog
%xor1 = xor i32 %a, %b
%xor2 = xor i32 %a, %c
%or = or i32 %xor1, %xor2
@@ -167,9 +214,9 @@ define amdgpu_ps float @test_12_src_overflow(i32 %a, i32 %b, i32 %c) {
;
; GFX950-GISEL-LABEL: test_12_src_overflow:
; GFX950-GISEL: ; %bb.0:
-; GFX950-GISEL-NEXT: v_bitop3_b32 v3, v0, v2, v0 bitop3:0xc
-; GFX950-GISEL-NEXT: v_bitop3_b32 v0, v0, v2, v0 bitop3:3
-; GFX950-GISEL-NEXT: v_bitop3_b32 v0, v3, v1, v0 bitop3:0xc8
+; GFX950-GISEL-NEXT: v_not_b32_e32 v0, v0
+; GFX950-GISEL-NEXT: v_bfi_b32 v0, v2, v0, v0
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v1
; GFX950-GISEL-NEXT: ; return to shader part epilog
%nota = xor i32 %a, -1
%notc = xor i32 %c, -1
@@ -185,13 +232,27 @@ define amdgpu_ps float @test_12_src_overflow(i32 %a, i32 %b, i32 %c) {
; This could be a single LOP3 operation with tbl = 100, but Src vector exhausted during search.
define amdgpu_ps float @test_100_src_overflow(i32 %a, i32 %b, i32 %c) {
-; GCN-LABEL: test_100_src_overflow:
-; GCN: ; %bb.0:
-; GCN-NEXT: v_bitop3_b32 v3, v1, v2, v0 bitop3:0x10
-; GCN-NEXT: v_bitop3_b32 v4, v0, v2, v1 bitop3:0x40
-; GCN-NEXT: v_bitop3_b32 v0, v1, v2, v0 bitop3:0x20
-; GCN-NEXT: v_or3_b32 v0, v3, v4, v0
-; GCN-NEXT: ; return to shader part epilog
+; GFX950-SDAG-LABEL: test_100_src_overflow:
+; GFX950-SDAG: ; %bb.0:
+; GFX950-SDAG-NEXT: v_bitop3_b32 v3, v1, v2, v0 bitop3:0x10
+; GFX950-SDAG-NEXT: v_bitop3_b32 v4, v0, v2, v1 bitop3:0x40
+; GFX950-SDAG-NEXT: v_bitop3_b32 v0, v1, v2, v0 bitop3:0x20
+; GFX950-SDAG-NEXT: v_or3_b32 v0, v3, v4, v0
+; GFX950-SDAG-NEXT: ; return to shader part epilog
+;
+; GFX950-GISEL-LABEL: test_100_src_overflow:
+; GFX950-GISEL: ; %bb.0:
+; GFX950-GISEL-NEXT: v_or_b32_e32 v3, v2, v0
+; GFX950-GISEL-NEXT: v_not_b32_e32 v3, v3
+; GFX950-GISEL-NEXT: v_not_b32_e32 v4, v1
+; GFX950-GISEL-NEXT: v_and_b32_e32 v3, v1, v3
+; GFX950-GISEL-NEXT: v_and_b32_e32 v4, v0, v4
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v1, v0
+; GFX950-GISEL-NEXT: v_not_b32_e32 v1, v2
+; GFX950-GISEL-NEXT: v_and_b32_e32 v4, v4, v2
+; GFX950-GISEL-NEXT: v_and_b32_e32 v0, v0, v1
+; GFX950-GISEL-NEXT: v_or3_b32 v0, v3, v4, v0
+; GFX950-GISEL-NEXT: ; return to shader part epilog
%or1 = or i32 %c, %a
%not1 = xor i32 %or1, -1
%and1 = and i32 %b, %not1
@@ -260,12 +321,19 @@ define amdgpu_ps float @uniform_3_op(i32 inreg %a, i32 inreg %b, i32 inreg %c) {
}
define amdgpu_ps float @uniform_4_op(i32 inreg %a, i32 inreg %b, i32 inreg %c) {
-; GCN-LABEL: uniform_4_op:
-; GCN: ; %bb.0:
-; GCN-NEXT: v_mov_b32_e32 v0, s1
-; GCN-NEXT: v_mov_b32_e32 v1, s2
-; GCN-NEXT: v_bitop3_b32 v0, s0, v0, v1 bitop3:2
-; GCN-NEXT: ; return to shader part epilog
+; GFX950-SDAG-LABEL: uniform_4_op:
+; GFX950-SDAG: ; %bb.0:
+; GFX950-SDAG-NEXT: v_mov_b32_e32 v0, s1
+; GFX950-SDAG-NEXT: v_mov_b32_e32 v1, s2
+; GFX950-SDAG-NEXT: v_bitop3_b32 v0, s0, v0, v1 bitop3:2
+; GFX950-SDAG-NEXT: ; return to shader part epilog
+;
+; GFX950-GISEL-LABEL: uniform_4_op:
+; GFX950-GISEL: ; %bb.0:
+; GFX950-GISEL-NEXT: s_andn2_b32 s0, s2, s0
+; GFX950-GISEL-NEXT: s_andn2_b32 s0, s0, s1
+; GFX950-GISEL-NEXT: v_mov_b32_e32 v0, s0
+; GFX950-GISEL-NEXT: ; return to shader part epilog
%nota = xor i32 %a, -1
%notb = xor i32 %b, -1
%and1 = and i32 %nota, %c
``````````
</details>
https://github.com/llvm/llvm-project/pull/117940
More information about the llvm-commits
mailing list