maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] Pattern for v_xor3_b32 

This also allows three op patterns to use increased constant bus
limit of GFX10.

Differential Revision: https://reviews.llvm.org/D61763

llvm-svn: 360395
This commit is contained in:
Stanislav Mekhanoshin 2019-05-10 00:09:01 +00:00
parent 4fa4df9cdc
commit 64196850f0
9 changed files with 405 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Target/AMDGPU/VOP3Instructions.td
View File

@ -560,7 +560,9 @@ class ThreeOpFrag<SDPatternOperator op1, SDPatternOperator op2> : PatFrag<
if (!Operands[i]->isDivergent() &&
!isInlineImmediate(Operands[i].getNode())) {
ConstantBusUses++;
if (ConstantBusUses >= 2)
// This uses AMDGPU::V_ADD3_U32, but all three operand instructions
// have the same constant bus limit.
if (ConstantBusUses > Subtarget->getConstantBusLimit(AMDGPU::V_ADD3_U32))
return false;
}
}
@ -625,6 +627,7 @@ def : ThreeOp_i32_Pats<xor, add, V_XAD_U32>;
let SubtargetPredicate = isGFX10Plus in {
def V_XOR3_B32 : VOP3Inst <"v_xor3_b32", VOP3_Profile<VOP_I32_I32_I32_I32>>;
def : ThreeOp_i32_Pats<xor, xor, V_XOR3_B32>;
} // End SubtargetPredicate = isGFX10Plus
//===----------------------------------------------------------------------===//

53
llvm/test/CodeGen/AMDGPU/add3.ll
View File

@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=fiji -verify-machineinstrs | FileCheck -check-prefix=VI %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GFX9 %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefix=GFX10 %s
; ===================================================================================
; V_ADD3_U32
@ -17,6 +18,11 @@ define amdgpu_ps float @add3(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add3_u32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add3:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add3_u32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -36,6 +42,12 @@ define amdgpu_ps float @mad_no_add3(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e) {
; GFX9-NEXT: v_mad_u32_u24 v0, v0, v1, v4
; GFX9-NEXT: v_mad_u32_u24 v0, v2, v3, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: mad_no_add3:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_mad_u32_u24 v0, v0, v1, v4
; GFX10-NEXT: v_mad_u32_u24 v0, v2, v3, v0
; GFX10-NEXT: ; return to shader part epilog
%a0 = shl i32 %a, 8
%a1 = lshr i32 %a0, 8
%b0 = shl i32 %b, 8
@ -69,6 +81,11 @@ define amdgpu_ps float @add3_vgpr_b(i32 inreg %a, i32 %b, i32 inreg %c) {
; GFX9-NEXT: s_add_i32 s3, s3, s2
; GFX9-NEXT: v_add_u32_e32 v0, s3, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add3_vgpr_b:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add3_u32 v0, s3, s2, v0
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -86,6 +103,11 @@ define amdgpu_ps float @add3_vgpr_all2(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add3_u32 v0, v1, v2, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add3_vgpr_all2:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add3_u32 v0, v1, v2, v0
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %b, %c
%result = add i32 %a, %x
%bc = bitcast i32 %result to float
@ -103,6 +125,11 @@ define amdgpu_ps float @add3_vgpr_bc(i32 inreg %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add3_u32 v0, s2, v0, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add3_vgpr_bc:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add3_u32 v0, s2, v0, v1
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -120,6 +147,11 @@ define amdgpu_ps float @add3_vgpr_const(i32 %a, i32 %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add3_u32 v0, v0, v1, 16
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add3_vgpr_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add3_u32 v0, v0, v1, 16
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = add i32 %x, 16
%bc = bitcast i32 %result to float
@ -139,6 +171,12 @@ define amdgpu_ps <2 x float> @add3_multiuse_outer(i32 %a, i32 %b, i32 %c, i32 %x
; GFX9-NEXT: v_add3_u32 v0, v0, v1, v2
; GFX9-NEXT: v_mul_lo_u32 v1, v0, v3
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add3_multiuse_outer:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add3_u32 v0, v0, v1, v2
; GFX10-NEXT: v_mul_lo_u32 v1, v0, v3
; GFX10-NEXT: ; return to shader part epilog
%inner = add i32 %a, %b
%outer = add i32 %inner, %c
%x1 = mul i32 %outer, %x
@ -160,6 +198,12 @@ define amdgpu_ps <2 x float> @add3_multiuse_inner(i32 %a, i32 %b, i32 %c) {
; GFX9-NEXT: v_add_u32_e32 v0, v0, v1
; GFX9-NEXT: v_add_u32_e32 v1, v0, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add3_multiuse_inner:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_nc_u32_e32 v0, v0, v1
; GFX10-NEXT: v_add_nc_u32_e32 v1, v0, v2
; GFX10-NEXT: ; return to shader part epilog
%inner = add i32 %a, %b
%outer = add i32 %inner, %c
%r1 = insertelement <2 x i32> undef, i32 %inner, i32 0
@ -190,6 +234,15 @@ define amdgpu_ps float @add3_uniform_vgpr(float inreg %a, float inreg %b, float
; GFX9-NEXT: v_add_u32_e32 v0, v0, v1
; GFX9-NEXT: v_add_u32_e32 v0, v0, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add3_uniform_vgpr:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_f32_e64 v1, s3, 2.0
; GFX10-NEXT: v_add_f32_e64 v2, s2, 1.0
; GFX10-NEXT: v_add_f32_e64 v0, 0x40400000, s4
; GFX10-NEXT: v_add_nc_u32_e32 v1, v2, v1
; GFX10-NEXT: v_add_nc_u32_e32 v0, v1, v0
; GFX10-NEXT: ; return to shader part epilog
%a1 = fadd float %a, 1.0
%b2 = fadd float %b, 2.0
%c3 = fadd float %c, 3.0

31
llvm/test/CodeGen/AMDGPU/add_shl.ll
View File

@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=fiji -verify-machineinstrs | FileCheck -check-prefix=VI %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GFX9 %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefix=GFX10 %s
; ===================================================================================
; V_ADD_LSHL_U32
@ -17,6 +18,11 @@ define amdgpu_ps float @add_shl(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add_lshl_u32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_lshl_u32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = shl i32 %x, %c
%bc = bitcast i32 %result to float
@ -35,6 +41,11 @@ define amdgpu_ps float @add_shl_vgpr_c(i32 inreg %a, i32 inreg %b, i32 %c) {
; GFX9-NEXT: s_add_i32 s2, s2, s3
; GFX9-NEXT: v_lshlrev_b32_e64 v0, v0, s2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_c:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_lshl_u32 v0, s2, s3, v0
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = shl i32 %x, %c
%bc = bitcast i32 %result to float
@ -52,6 +63,11 @@ define amdgpu_ps float @add_shl_vgpr_ac(i32 %a, i32 inreg %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add_lshl_u32 v0, v0, s2, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_ac:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_lshl_u32 v0, v0, s2, v1
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = shl i32 %x, %c
%bc = bitcast i32 %result to float
@ -69,6 +85,11 @@ define amdgpu_ps float @add_shl_vgpr_const(i32 %a, i32 %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add_lshl_u32 v0, v0, v1, 9
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_lshl_u32 v0, v0, v1, 9
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = shl i32 %x, 9
%bc = bitcast i32 %result to float
@ -87,6 +108,11 @@ define amdgpu_ps float @add_shl_vgpr_const_inline_const(i32 %a) {
; GFX9-NEXT: v_mov_b32_e32 v1, 0x7e800
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 9, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_const_inline_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_add_u32 v0, v0, 9, 0x7e800
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, 1012
%result = shl i32 %x, 9
%bc = bitcast i32 %result to float
@ -108,6 +134,11 @@ define amdgpu_ps float @add_shl_vgpr_inline_const_x2(i32 %a) {
; GFX9-NEXT: v_mov_b32_e32 v1, 0x600
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 9, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_inline_const_x2:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_add_u32 v0, v0, 9, 0x600
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, 3
%result = shl i32 %x, 9
%bc = bitcast i32 %result to float

31
llvm/test/CodeGen/AMDGPU/and_or.ll
View File

@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
;RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=fiji -verify-machineinstrs | FileCheck -check-prefix=VI %s
;RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GFX9 %s
;RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefix=GFX10 %s
; ===================================================================================
; V_AND_OR_B32
@ -17,6 +18,11 @@ define amdgpu_ps float @and_or(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_and_or_b32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: and_or:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_and_or_b32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = and i32 %a, %b
%result = or i32 %x, %c
%bc = bitcast i32 %result to float
@ -36,6 +42,11 @@ define amdgpu_ps float @and_or_vgpr_b(i32 inreg %a, i32 %b, i32 inreg %c) {
; GFX9-NEXT: v_and_b32_e32 v0, s2, v0
; GFX9-NEXT: v_or_b32_e32 v0, s3, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: and_or_vgpr_b:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_and_or_b32 v0, s2, v0, s3
; GFX10-NEXT: ; return to shader part epilog
%x = and i32 %a, %b
%result = or i32 %x, %c
%bc = bitcast i32 %result to float
@ -53,6 +64,11 @@ define amdgpu_ps float @and_or_vgpr_ab(i32 %a, i32 %b, i32 inreg %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_and_or_b32 v0, v0, v1, s2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: and_or_vgpr_ab:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_and_or_b32 v0, v0, v1, s2
; GFX10-NEXT: ; return to shader part epilog
%x = and i32 %a, %b
%result = or i32 %x, %c
%bc = bitcast i32 %result to float
@ -70,6 +86,11 @@ define amdgpu_ps float @and_or_vgpr_const(i32 %a, i32 %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_and_or_b32 v0, v0, 4, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: and_or_vgpr_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_and_or_b32 v0, v0, 4, v1
; GFX10-NEXT: ; return to shader part epilog
%x = and i32 4, %a
%result = or i32 %x, %b
%bc = bitcast i32 %result to float
@ -88,6 +109,11 @@ define amdgpu_ps float @and_or_vgpr_const_inline_const(i32 %a) {
; GFX9-NEXT: v_mov_b32_e32 v1, 0x808
; GFX9-NEXT: v_and_or_b32 v0, v0, 20, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: and_or_vgpr_const_inline_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_and_or_b32 v0, v0, 20, 0x808
; GFX10-NEXT: ; return to shader part epilog
%x = and i32 20, %a
%result = or i32 %x, 2056
%bc = bitcast i32 %result to float
@ -105,6 +131,11 @@ define amdgpu_ps float @and_or_vgpr_inline_const_x2(i32 %a) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_and_or_b32 v0, v0, 4, 1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: and_or_vgpr_inline_const_x2:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_and_or_b32 v0, v0, 4, 1
; GFX10-NEXT: ; return to shader part epilog
%x = and i32 4, %a
%result = or i32 %x, 1
%bc = bitcast i32 %result to float

26
llvm/test/CodeGen/AMDGPU/or3.ll
View File

@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=fiji -verify-machineinstrs | FileCheck -check-prefix=VI %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GFX9 %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefix=GFX10 %s
; ===================================================================================
; V_OR3_B32
@ -17,6 +18,11 @@ define amdgpu_ps float @or3(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_or3_b32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: or3:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_or3_b32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = or i32 %a, %b
%result = or i32 %x, %c
%bc = bitcast i32 %result to float
@ -37,6 +43,11 @@ define amdgpu_ps float @or3_vgpr_a(i32 %a, i32 inreg %b, i32 inreg %c) {
; GFX9-NEXT: v_or_b32_e32 v0, s2, v0
; GFX9-NEXT: v_or_b32_e32 v0, s3, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: or3_vgpr_a:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_or3_b32 v0, v0, s2, s3
; GFX10-NEXT: ; return to shader part epilog
%x = or i32 %a, %b
%result = or i32 %x, %c
%bc = bitcast i32 %result to float
@ -54,6 +65,11 @@ define amdgpu_ps float @or3_vgpr_all2(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_or3_b32 v0, v1, v2, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: or3_vgpr_all2:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_or3_b32 v0, v1, v2, v0
; GFX10-NEXT: ; return to shader part epilog
%x = or i32 %b, %c
%result = or i32 %a, %x
%bc = bitcast i32 %result to float
@ -71,6 +87,11 @@ define amdgpu_ps float @or3_vgpr_bc(i32 inreg %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_or3_b32 v0, s2, v0, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: or3_vgpr_bc:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_or3_b32 v0, s2, v0, v1
; GFX10-NEXT: ; return to shader part epilog
%x = or i32 %a, %b
%result = or i32 %x, %c
%bc = bitcast i32 %result to float
@ -88,6 +109,11 @@ define amdgpu_ps float @or3_vgpr_const(i32 %a, i32 %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_or3_b32 v0, v1, v0, 64
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: or3_vgpr_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_or3_b32 v0, v1, v0, 64
; GFX10-NEXT: ; return to shader part epilog
%x = or i32 64, %b
%result = or i32 %x, %a
%bc = bitcast i32 %result to float

26
llvm/test/CodeGen/AMDGPU/shl_add.ll
View File

@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=fiji -verify-machineinstrs | FileCheck -check-prefix=VI %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GFX9 %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefix=GFX10 %s
; ===================================================================================
; V_LSHL_ADD_U32
@ -17,6 +18,11 @@ define amdgpu_ps float @shl_add(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_add_u32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_add:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_add_u32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -36,6 +42,11 @@ define amdgpu_ps float @shl_add_vgpr_a(i32 %a, i32 inreg %b, i32 inreg %c) {
; GFX9-NEXT: v_lshlrev_b32_e32 v0, s2, v0
; GFX9-NEXT: v_add_u32_e32 v0, s3, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_add_vgpr_a:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_add_u32 v0, v0, s2, s3
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -53,6 +64,11 @@ define amdgpu_ps float @shl_add_vgpr_all(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_add_u32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_add_vgpr_all:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_add_u32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -70,6 +86,11 @@ define amdgpu_ps float @shl_add_vgpr_ab(i32 %a, i32 %b, i32 inreg %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_add_u32 v0, v0, v1, s2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_add_vgpr_ab:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_add_u32 v0, v0, v1, s2
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -87,6 +108,11 @@ define amdgpu_ps float @shl_add_vgpr_const(i32 %a, i32 %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 3, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_add_vgpr_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_add_u32 v0, v0, 3, v1
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, 3
%result = add i32 %x, %b
%bc = bitcast i32 %result to float

41
llvm/test/CodeGen/AMDGPU/shl_or.ll
View File

@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=fiji -verify-machineinstrs | FileCheck -check-prefix=VI %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GFX9 %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefix=GFX10 %s
; ===================================================================================
; V_LSHL_OR_B32
@ -17,6 +18,11 @@ define amdgpu_ps float @shl_or(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_or_b32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_or:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_or_b32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, %b
%result = or i32 %x, %c
%bc = bitcast i32 %result to float
@ -35,6 +41,11 @@ define amdgpu_ps float @shl_or_vgpr_c(i32 inreg %a, i32 inreg %b, i32 %c) {
; GFX9-NEXT: s_lshl_b32 s0, s2, s3
; GFX9-NEXT: v_or_b32_e32 v0, s0, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_or_vgpr_c:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_or_b32 v0, s2, s3, v0
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, %b
%result = or i32 %x, %c
%bc = bitcast i32 %result to float
@ -52,6 +63,11 @@ define amdgpu_ps float @shl_or_vgpr_all2(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_or_b32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_or_vgpr_all2:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_or_b32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, %b
%result = or i32 %c, %x
%bc = bitcast i32 %result to float
@ -69,6 +85,11 @@ define amdgpu_ps float @shl_or_vgpr_ac(i32 %a, i32 inreg %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_or_b32 v0, v0, s2, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_or_vgpr_ac:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_or_b32 v0, v0, s2, v1
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, %b
%result = or i32 %x, %c
%bc = bitcast i32 %result to float
@ -86,6 +107,11 @@ define amdgpu_ps float @shl_or_vgpr_const(i32 %a, i32 %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_or_b32 v0, v0, v1, 6
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_or_vgpr_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_or_b32 v0, v0, v1, 6
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, %b
%result = or i32 %x, 6
%bc = bitcast i32 %result to float
@ -103,6 +129,11 @@ define amdgpu_ps float @shl_or_vgpr_const2(i32 %a, i32 %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_or_b32 v0, v0, 6, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_or_vgpr_const2:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_or_b32 v0, v0, 6, v1
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, 6
%result = or i32 %x, %b
%bc = bitcast i32 %result to float
@ -120,6 +151,11 @@ define amdgpu_ps float @shl_or_vgpr_const_scalar1(i32 inreg %a, i32 %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_or_b32 v0, s2, 6, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_or_vgpr_const_scalar1:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_or_b32 v0, s2, 6, v0
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, 6
%result = or i32 %x, %b
%bc = bitcast i32 %result to float
@ -137,6 +173,11 @@ define amdgpu_ps float @shl_or_vgpr_const_scalar2(i32 %a, i32 inreg %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_lshl_or_b32 v0, v0, 6, s2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: shl_or_vgpr_const_scalar2:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_or_b32 v0, v0, 6, s2
; GFX10-NEXT: ; return to shader part epilog
%x = shl i32 %a, 6
%result = or i32 %x, %b
%bc = bitcast i32 %result to float

167
llvm/test/CodeGen/AMDGPU/xor3.ll Normal file
View File

@ -0,0 +1,167 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GFX9 %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefix=GFX10 %s
; ===================================================================================
; V_XOR3_B32
; ===================================================================================
define amdgpu_ps float @xor3(i32 %a, i32 %b, i32 %c) {
; GFX9-LABEL: xor3:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v1
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor3:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xor3_b32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %a, %b
%result = xor i32 %x, %c
%bc = bitcast i32 %result to float
ret float %bc
}
define amdgpu_ps float @xor3_vgpr_b(i32 inreg %a, i32 %b, i32 inreg %c) {
; GFX9-LABEL: xor3_vgpr_b:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xor_b32_e32 v0, s2, v0
; GFX9-NEXT: v_xor_b32_e32 v0, s3, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor3_vgpr_b:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xor3_b32 v0, s2, v0, s3
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %a, %b
%result = xor i32 %x, %c
%bc = bitcast i32 %result to float
ret float %bc
}
define amdgpu_ps float @xor3_vgpr_all2(i32 %a, i32 %b, i32 %c) {
; GFX9-LABEL: xor3_vgpr_all2:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xor_b32_e32 v1, v1, v2
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor3_vgpr_all2:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xor3_b32 v0, v1, v2, v0
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %b, %c
%result = xor i32 %a, %x
%bc = bitcast i32 %result to float
ret float %bc
}
define amdgpu_ps float @xor3_vgpr_bc(i32 inreg %a, i32 %b, i32 %c) {
; GFX9-LABEL: xor3_vgpr_bc:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xor_b32_e32 v0, s2, v0
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor3_vgpr_bc:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xor3_b32 v0, s2, v0, v1
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %a, %b
%result = xor i32 %x, %c
%bc = bitcast i32 %result to float
ret float %bc
}
define amdgpu_ps float @xor3_vgpr_const(i32 %a, i32 %b) {
; GFX9-LABEL: xor3_vgpr_const:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v1
; GFX9-NEXT: v_xor_b32_e32 v0, 16, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor3_vgpr_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xor3_b32 v0, v0, v1, 16
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %a, %b
%result = xor i32 %x, 16
%bc = bitcast i32 %result to float
ret float %bc
}
define amdgpu_ps <2 x float> @xor3_multiuse_outer(i32 %a, i32 %b, i32 %c, i32 %x) {
; GFX9-LABEL: xor3_multiuse_outer:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v1
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v2
; GFX9-NEXT: v_mul_lo_u32 v1, v0, v3
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor3_multiuse_outer:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xor3_b32 v0, v0, v1, v2
; GFX10-NEXT: v_mul_lo_u32 v1, v0, v3
; GFX10-NEXT: ; return to shader part epilog
%inner = xor i32 %a, %b
%outer = xor i32 %inner, %c
%x1 = mul i32 %outer, %x
%r1 = insertelement <2 x i32> undef, i32 %outer, i32 0
%r0 = insertelement <2 x i32> %r1, i32 %x1, i32 1
%bc = bitcast <2 x i32> %r0 to <2 x float>
ret <2 x float> %bc
}
define amdgpu_ps <2 x float> @xor3_multiuse_inner(i32 %a, i32 %b, i32 %c) {
; GFX9-LABEL: xor3_multiuse_inner:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v1
; GFX9-NEXT: v_xor_b32_e32 v1, v0, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor3_multiuse_inner:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xor_b32_e32 v0, v0, v1
; GFX10-NEXT: v_xor_b32_e32 v1, v0, v2
; GFX10-NEXT: ; return to shader part epilog
%inner = xor i32 %a, %b
%outer = xor i32 %inner, %c
%r1 = insertelement <2 x i32> undef, i32 %inner, i32 0
%r0 = insertelement <2 x i32> %r1, i32 %outer, i32 1
%bc = bitcast <2 x i32> %r0 to <2 x float>
ret <2 x float> %bc
}
; A case where uniform values end up in VGPRs -- we could use v_xor3_b32 here,
; but we don't.
define amdgpu_ps float @xor3_uniform_vgpr(float inreg %a, float inreg %b, float inreg %c) {
; GFX9-LABEL: xor3_uniform_vgpr:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_mov_b32_e32 v2, 0x40400000
; GFX9-NEXT: v_add_f32_e64 v0, s2, 1.0
; GFX9-NEXT: v_add_f32_e64 v1, s3, 2.0
; GFX9-NEXT: v_add_f32_e32 v2, s4, v2
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v1
; GFX9-NEXT: v_xor_b32_e32 v0, v0, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor3_uniform_vgpr:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_f32_e64 v1, s3, 2.0
; GFX10-NEXT: v_add_f32_e64 v2, s2, 1.0
; GFX10-NEXT: v_add_f32_e64 v0, 0x40400000, s4
; GFX10-NEXT: v_xor_b32_e32 v1, v2, v1
; GFX10-NEXT: v_xor_b32_e32 v0, v1, v0
; GFX10-NEXT: ; return to shader part epilog
%a1 = fadd float %a, 1.0
%b2 = fadd float %b, 2.0
%c3 = fadd float %c, 3.0
%bc.a = bitcast float %a1 to i32
%bc.b = bitcast float %b2 to i32
%bc.c = bitcast float %c3 to i32
%x = xor i32 %bc.a, %bc.b
%result = xor i32 %x, %bc.c
%bc = bitcast i32 %result to float
ret float %bc
}

26
llvm/test/CodeGen/AMDGPU/xor_add.ll
View File

@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=fiji -verify-machineinstrs | FileCheck -check-prefix=VI %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GFX9 %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefix=GFX10 %s
; ===================================================================================
; V_XAD_U32
@ -17,6 +18,11 @@ define amdgpu_ps float @xor_add(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xad_u32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor_add:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xad_u32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -36,6 +42,11 @@ define amdgpu_ps float @xor_add_vgpr_a(i32 %a, i32 inreg %b, i32 inreg %c) {
; GFX9-NEXT: v_xor_b32_e32 v0, s2, v0
; GFX9-NEXT: v_add_u32_e32 v0, s3, v0
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor_add_vgpr_a:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xad_u32 v0, v0, s2, s3
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -53,6 +64,11 @@ define amdgpu_ps float @xor_add_vgpr_all(i32 %a, i32 %b, i32 %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xad_u32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor_add_vgpr_all:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xad_u32 v0, v0, v1, v2
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -70,6 +86,11 @@ define amdgpu_ps float @xor_add_vgpr_ab(i32 %a, i32 %b, i32 inreg %c) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xad_u32 v0, v0, v1, s2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor_add_vgpr_ab:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xad_u32 v0, v0, v1, s2
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %a, %b
%result = add i32 %x, %c
%bc = bitcast i32 %result to float
@ -87,6 +108,11 @@ define amdgpu_ps float @xor_add_vgpr_const(i32 %a, i32 %b) {
; GFX9: ; %bb.0:
; GFX9-NEXT: v_xad_u32 v0, v0, 3, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: xor_add_vgpr_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_xad_u32 v0, v0, 3, v1
; GFX10-NEXT: ; return to shader part epilog
%x = xor i32 %a, 3
%result = add i32 %x, %b
%bc = bitcast i32 %result to float