maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/InstCombine/bitcast.ll

212 lines
6.5 KiB
LLVM
Raw Normal View History

filecheckize llvm-svn: 112225
2010-08-27 05:51:41 +08:00
; RUN: opt < %s -instcombine -S | FileCheck %s
Fix an instcombine abort on a scalar-to-vector bitcast. This fixes PR4487. llvm-svn: 74646
2009-07-02 05:38:46 +08:00
Add constant folding support for bitcasts of splat vectors to integers. llvm-svn: 138206
2011-08-20 22:02:29 +08:00
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-apple-darwin10.0.0"
filecheckize llvm-svn: 112225
2010-08-27 05:51:41 +08:00
; Bitcasts between vectors and scalars are valid.
; PR4487
define i32 @test1(i64 %a) {
Fix an instcombine abort on a scalar-to-vector bitcast. This fixes PR4487. llvm-svn: 74646
2009-07-02 05:38:46 +08:00
%t1 = bitcast i64 %a to <2 x i32>
%t2 = bitcast i64 %a to <2 x i32>
%t3 = xor <2 x i32> %t1, %t2
%t4 = extractelement <2 x i32> %t3, i32 0
ret i32 %t4
Remove trailing whitespace llvm-svn: 174903
2013-02-12 05:36:49 +08:00
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test1(
filecheckize llvm-svn: 112225
2010-08-27 05:51:41 +08:00
; CHECK: ret i32 0
Fix an instcombine abort on a scalar-to-vector bitcast. This fixes PR4487. llvm-svn: 74646
2009-07-02 05:38:46 +08:00
}
optimize bitcast(trunc(bitcast(x))) where the result is a float and 'x' is a vector to be a vector element extraction. This allows clang to compile: struct S { float A, B, C, D; }; float foo(struct S A) { return A.A + A.B+A.C+A.D; } into: _foo: ## @foo ## BB#0: ## %entry movd %xmm0, %rax shrq $32, %rax movd %eax, %xmm2 addss %xmm0, %xmm2 movapd %xmm1, %xmm3 addss %xmm2, %xmm3 movd %xmm1, %rax shrq $32, %rax movd %eax, %xmm0 addss %xmm3, %xmm0 ret instead of: _foo: ## @foo ## BB#0: ## %entry movd %xmm0, %rax movd %eax, %xmm0 shrq $32, %rax movd %eax, %xmm2 addss %xmm0, %xmm2 movd %xmm1, %rax movd %eax, %xmm1 addss %xmm2, %xmm1 shrq $32, %rax movd %eax, %xmm0 addss %xmm1, %xmm0 ret ... eliminating half of the horribleness. llvm-svn: 112227
2010-08-27 05:55:42 +08:00
; Optimize bitcasts that are extracting low element of vector. This happens
; because of SRoA.
; rdar://7892780
define float @test2(<2 x float> %A, <2 x i32> %B) {
%tmp28 = bitcast <2 x float> %A to i64 ; <i64> [#uses=2]
%tmp23 = trunc i64 %tmp28 to i32 ; <i32> [#uses=1]
%tmp24 = bitcast i32 %tmp23 to float ; <float> [#uses=1]
%tmp = bitcast <2 x i32> %B to i64
%tmp2 = trunc i64 %tmp to i32 ; <i32> [#uses=1]
%tmp4 = bitcast i32 %tmp2 to float ; <float> [#uses=1]
%add = fadd float %tmp24, %tmp4
ret float %add
Remove trailing whitespace llvm-svn: 174903
2013-02-12 05:36:49 +08:00
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test2(
optimize bitcast(trunc(bitcast(x))) where the result is a float and 'x' is a vector to be a vector element extraction. This allows clang to compile: struct S { float A, B, C, D; }; float foo(struct S A) { return A.A + A.B+A.C+A.D; } into: _foo: ## @foo ## BB#0: ## %entry movd %xmm0, %rax shrq $32, %rax movd %eax, %xmm2 addss %xmm0, %xmm2 movapd %xmm1, %xmm3 addss %xmm2, %xmm3 movd %xmm1, %rax shrq $32, %rax movd %eax, %xmm0 addss %xmm3, %xmm0 ret instead of: _foo: ## @foo ## BB#0: ## %entry movd %xmm0, %rax movd %eax, %xmm0 shrq $32, %rax movd %eax, %xmm2 addss %xmm0, %xmm2 movd %xmm1, %rax movd %eax, %xmm1 addss %xmm2, %xmm1 shrq $32, %rax movd %eax, %xmm0 addss %xmm1, %xmm0 ret ... eliminating half of the horribleness. llvm-svn: 112227
2010-08-27 05:55:42 +08:00
; CHECK-NEXT: %tmp24 = extractelement <2 x float> %A, i32 0
; CHECK-NEXT: bitcast <2 x i32> %B to <2 x float>
; CHECK-NEXT: %tmp4 = extractelement <2 x float> {{.*}}, i32 0
; CHECK-NEXT: %add = fadd float %tmp24, %tmp4
; CHECK-NEXT: ret float %add
}
optimize "integer extraction out of the middle of a vector" as produced by SRoA. This is part of rdar://7892780, but needs another xform to expose this. llvm-svn: 112232
2010-08-27 06:14:59 +08:00
; Optimize bitcasts that are extracting other elements of a vector. This
; happens because of SRoA.
; rdar://7892780
define float @test3(<2 x float> %A, <2 x i64> %B) {
%tmp28 = bitcast <2 x float> %A to i64
%tmp29 = lshr i64 %tmp28, 32
%tmp23 = trunc i64 %tmp29 to i32
%tmp24 = bitcast i32 %tmp23 to float
%tmp = bitcast <2 x i64> %B to i128
%tmp1 = lshr i128 %tmp, 64
%tmp2 = trunc i128 %tmp1 to i32
%tmp4 = bitcast i32 %tmp2 to float
%add = fadd float %tmp24, %tmp4
ret float %add
Remove trailing whitespace llvm-svn: 174903
2013-02-12 05:36:49 +08:00
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test3(
optimize "integer extraction out of the middle of a vector" as produced by SRoA. This is part of rdar://7892780, but needs another xform to expose this. llvm-svn: 112232
2010-08-27 06:14:59 +08:00
; CHECK-NEXT: %tmp24 = extractelement <2 x float> %A, i32 1
; CHECK-NEXT: bitcast <2 x i64> %B to <4 x float>
; CHECK-NEXT: %tmp4 = extractelement <4 x float> {{.*}}, i32 2
; CHECK-NEXT: %add = fadd float %tmp24, %tmp4
; CHECK-NEXT: ret float %add
}
optimize bitcasts from large integers to vector into vector element insertion from the pieces that feed into the vector. This handles a pattern that occurs frequently due to code generated for the x86-64 abi. We now compile something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.A; ++A.C; return A; } into all nice vector operations: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 12(%rax), %xmm3 pshufd $16, %xmm2, %xmm2 unpcklps %xmm2, %xmm0 addss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 pshufd $16, %xmm3, %xmm2 unpcklps %xmm2, %xmm1 ret instead of icky integer operations: _bar: ## @bar movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 movd %xmm0, %ecx movl 4(%rax), %edx movl 12(%rax), %esi shlq $32, %rdx addq %rcx, %rdx movd %rdx, %xmm0 addss 8(%rax), %xmm1 movd %xmm1, %eax shlq $32, %rsi addq %rax, %rsi movd %rsi, %xmm1 ret This resolves rdar://8360454 llvm-svn: 112343
2010-08-28 09:20:38 +08:00
[InstCombine] fold bitcasts around an extractelement (3rd try) This is a redo of r255137 (reverted at r255227) which was a redo of r255124 (reverted at r255126) with a fixed check for a scalar source type and an added test for the failure that caused the revert. Original commit message: Example: bitcast (extractelement (bitcast <2 x float> %X to <2 x i32>), 1) to float ---> extractelement <2 x float> %X, i32 1 This is part of fixing PR25543: https://llvm.org/bugs/show_bug.cgi?id=25543 The next step will be to generalize this fold: trunc ( lshr ( bitcast X) ) -> extractelement (X) Ie, I'm hoping to replace the existing transform of: bitcast ( trunc ( lshr ( bitcast X))) added by: http://reviews.llvm.org/rL112232 with 2 less specific transforms to catch the case in the bug report. Differential Revision: http://reviews.llvm.org/D14879 llvm-svn: 255261
2015-12-11 01:09:28 +08:00
; Both bitcasts are unnecessary; change the extractelement.
[InstCombine] add tests to show missing bitcast optimizations llvm-svn: 253602
2015-11-20 05:32:25 +08:00
define float @bitcast_extelt1(<2 x float> %A) {
%bc1 = bitcast <2 x float> %A to <2 x i32>
%ext = extractelement <2 x i32> %bc1, i32 0
%bc2 = bitcast i32 %ext to float
ret float %bc2
; CHECK-LABEL: @bitcast_extelt1(
[InstCombine] fold bitcasts around an extractelement (3rd try) This is a redo of r255137 (reverted at r255227) which was a redo of r255124 (reverted at r255126) with a fixed check for a scalar source type and an added test for the failure that caused the revert. Original commit message: Example: bitcast (extractelement (bitcast <2 x float> %X to <2 x i32>), 1) to float ---> extractelement <2 x float> %X, i32 1 This is part of fixing PR25543: https://llvm.org/bugs/show_bug.cgi?id=25543 The next step will be to generalize this fold: trunc ( lshr ( bitcast X) ) -> extractelement (X) Ie, I'm hoping to replace the existing transform of: bitcast ( trunc ( lshr ( bitcast X))) added by: http://reviews.llvm.org/rL112232 with 2 less specific transforms to catch the case in the bug report. Differential Revision: http://reviews.llvm.org/D14879 llvm-svn: 255261
2015-12-11 01:09:28 +08:00
; CHECK-NEXT: %bc2 = extractelement <2 x float> %A, i32 0
[InstCombine] add tests to show missing bitcast optimizations llvm-svn: 253602
2015-11-20 05:32:25 +08:00
; CHECK-NEXT: ret float %bc2
}
[InstCombine] fold bitcasts around an extractelement (3rd try) This is a redo of r255137 (reverted at r255227) which was a redo of r255124 (reverted at r255126) with a fixed check for a scalar source type and an added test for the failure that caused the revert. Original commit message: Example: bitcast (extractelement (bitcast <2 x float> %X to <2 x i32>), 1) to float ---> extractelement <2 x float> %X, i32 1 This is part of fixing PR25543: https://llvm.org/bugs/show_bug.cgi?id=25543 The next step will be to generalize this fold: trunc ( lshr ( bitcast X) ) -> extractelement (X) Ie, I'm hoping to replace the existing transform of: bitcast ( trunc ( lshr ( bitcast X))) added by: http://reviews.llvm.org/rL112232 with 2 less specific transforms to catch the case in the bug report. Differential Revision: http://reviews.llvm.org/D14879 llvm-svn: 255261
2015-12-11 01:09:28 +08:00
; Second bitcast can be folded into the first.
[InstCombine] add tests to show missing bitcast optimizations llvm-svn: 253602
2015-11-20 05:32:25 +08:00
define i64 @bitcast_extelt2(<4 x float> %A) {
%bc1 = bitcast <4 x float> %A to <2 x double>
%ext = extractelement <2 x double> %bc1, i32 1
%bc2 = bitcast double %ext to i64
ret i64 %bc2
; CHECK-LABEL: @bitcast_extelt2(
[InstCombine] fold bitcasts around an extractelement (3rd try) This is a redo of r255137 (reverted at r255227) which was a redo of r255124 (reverted at r255126) with a fixed check for a scalar source type and an added test for the failure that caused the revert. Original commit message: Example: bitcast (extractelement (bitcast <2 x float> %X to <2 x i32>), 1) to float ---> extractelement <2 x float> %X, i32 1 This is part of fixing PR25543: https://llvm.org/bugs/show_bug.cgi?id=25543 The next step will be to generalize this fold: trunc ( lshr ( bitcast X) ) -> extractelement (X) Ie, I'm hoping to replace the existing transform of: bitcast ( trunc ( lshr ( bitcast X))) added by: http://reviews.llvm.org/rL112232 with 2 less specific transforms to catch the case in the bug report. Differential Revision: http://reviews.llvm.org/D14879 llvm-svn: 255261
2015-12-11 01:09:28 +08:00
; CHECK-NEXT: %bc = bitcast <4 x float> %A to <2 x i64>
; CHECK-NEXT: %bc2 = extractelement <2 x i64> %bc, i32 1
[InstCombine] add tests to show missing bitcast optimizations llvm-svn: 253602
2015-11-20 05:32:25 +08:00
; CHECK-NEXT: ret i64 %bc2
}
optimize bitcasts from large integers to vector into vector element insertion from the pieces that feed into the vector. This handles a pattern that occurs frequently due to code generated for the x86-64 abi. We now compile something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.A; ++A.C; return A; } into all nice vector operations: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 12(%rax), %xmm3 pshufd $16, %xmm2, %xmm2 unpcklps %xmm2, %xmm0 addss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 pshufd $16, %xmm3, %xmm2 unpcklps %xmm2, %xmm1 ret instead of icky integer operations: _bar: ## @bar movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 movd %xmm0, %ecx movl 4(%rax), %edx movl 12(%rax), %esi shlq $32, %rdx addq %rcx, %rdx movd %rdx, %xmm0 addss 8(%rax), %xmm1 movd %xmm1, %eax shlq $32, %rsi addq %rax, %rsi movd %rsi, %xmm1 ret This resolves rdar://8360454 llvm-svn: 112343
2010-08-28 09:20:38 +08:00
[InstCombine] fold bitcasts around an extractelement (3rd try) This is a redo of r255137 (reverted at r255227) which was a redo of r255124 (reverted at r255126) with a fixed check for a scalar source type and an added test for the failure that caused the revert. Original commit message: Example: bitcast (extractelement (bitcast <2 x float> %X to <2 x i32>), 1) to float ---> extractelement <2 x float> %X, i32 1 This is part of fixing PR25543: https://llvm.org/bugs/show_bug.cgi?id=25543 The next step will be to generalize this fold: trunc ( lshr ( bitcast X) ) -> extractelement (X) Ie, I'm hoping to replace the existing transform of: bitcast ( trunc ( lshr ( bitcast X))) added by: http://reviews.llvm.org/rL112232 with 2 less specific transforms to catch the case in the bug report. Differential Revision: http://reviews.llvm.org/D14879 llvm-svn: 255261
2015-12-11 01:09:28 +08:00
; TODO: This should return %A.
define <2 x i32> @bitcast_extelt3(<2 x i32> %A) {
%bc1 = bitcast <2 x i32> %A to <1 x i64>
%ext = extractelement <1 x i64> %bc1, i32 0
%bc2 = bitcast i64 %ext to <2 x i32>
ret <2 x i32> %bc2
; CHECK-LABEL: @bitcast_extelt3(
; CHECK-NEXT: %bc1 = bitcast <2 x i32> %A to <1 x i64>
; CHECK-NEXT: %ext = extractelement <1 x i64> %bc1, i32 0
; CHECK-NEXT: %bc2 = bitcast i64 %ext to <2 x i32>
; CHECK-NEXT: ret <2 x i32> %bc2
}
; Handle the case where the input is not a vector.
define double @bitcast_extelt4(i128 %A) {
%bc1 = bitcast i128 %A to <2 x i64>
%ext = extractelement <2 x i64> %bc1, i32 0
%bc2 = bitcast i64 %ext to double
ret double %bc2
; CHECK-LABEL: @bitcast_extelt4(
; CHECK-NEXT: %bc = bitcast i128 %A to <2 x double>
; CHECK-NEXT: %bc2 = extractelement <2 x double> %bc, i32 0
; CHECK-NEXT: ret double %bc2
}
optimize bitcasts from large integers to vector into vector element insertion from the pieces that feed into the vector. This handles a pattern that occurs frequently due to code generated for the x86-64 abi. We now compile something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.A; ++A.C; return A; } into all nice vector operations: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 12(%rax), %xmm3 pshufd $16, %xmm2, %xmm2 unpcklps %xmm2, %xmm0 addss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 pshufd $16, %xmm3, %xmm2 unpcklps %xmm2, %xmm1 ret instead of icky integer operations: _bar: ## @bar movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 movd %xmm0, %ecx movl 4(%rax), %edx movl 12(%rax), %esi shlq $32, %rdx addq %rcx, %rdx movd %rdx, %xmm0 addss 8(%rax), %xmm1 movd %xmm1, %eax shlq $32, %rsi addq %rax, %rsi movd %rsi, %xmm1 ret This resolves rdar://8360454 llvm-svn: 112343
2010-08-28 09:20:38 +08:00
define <2 x i32> @test4(i32 %A, i32 %B){
%tmp38 = zext i32 %A to i64
%tmp32 = zext i32 %B to i64
%tmp33 = shl i64 %tmp32, 32
%ins35 = or i64 %tmp33, %tmp38
%tmp43 = bitcast i64 %ins35 to <2 x i32>
ret <2 x i32> %tmp43
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test4(
optimize bitcasts from large integers to vector into vector element insertion from the pieces that feed into the vector. This handles a pattern that occurs frequently due to code generated for the x86-64 abi. We now compile something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.A; ++A.C; return A; } into all nice vector operations: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 12(%rax), %xmm3 pshufd $16, %xmm2, %xmm2 unpcklps %xmm2, %xmm0 addss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 pshufd $16, %xmm3, %xmm2 unpcklps %xmm2, %xmm1 ret instead of icky integer operations: _bar: ## @bar movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 movd %xmm0, %ecx movl 4(%rax), %edx movl 12(%rax), %esi shlq $32, %rdx addq %rcx, %rdx movd %rdx, %xmm0 addss 8(%rax), %xmm1 movd %xmm1, %eax shlq $32, %rsi addq %rax, %rsi movd %rsi, %xmm1 ret This resolves rdar://8360454 llvm-svn: 112343
2010-08-28 09:20:38 +08:00
; CHECK-NEXT: insertelement <2 x i32> undef, i32 %A, i32 0
; CHECK-NEXT: insertelement <2 x i32> {{.*}}, i32 %B, i32 1
Remove trailing whitespace llvm-svn: 174903
2013-02-12 05:36:49 +08:00
; CHECK-NEXT: ret <2 x i32>
optimize bitcasts from large integers to vector into vector element insertion from the pieces that feed into the vector. This handles a pattern that occurs frequently due to code generated for the x86-64 abi. We now compile something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.A; ++A.C; return A; } into all nice vector operations: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 12(%rax), %xmm3 pshufd $16, %xmm2, %xmm2 unpcklps %xmm2, %xmm0 addss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 pshufd $16, %xmm3, %xmm2 unpcklps %xmm2, %xmm1 ret instead of icky integer operations: _bar: ## @bar movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 movd %xmm0, %ecx movl 4(%rax), %edx movl 12(%rax), %esi shlq $32, %rdx addq %rcx, %rdx movd %rdx, %xmm0 addss 8(%rax), %xmm1 movd %xmm1, %eax shlq $32, %rsi addq %rax, %rsi movd %rsi, %xmm1 ret This resolves rdar://8360454 llvm-svn: 112343
2010-08-28 09:20:38 +08:00
}
; rdar://8360454
define <2 x float> @test5(float %A, float %B) {
%tmp37 = bitcast float %A to i32
%tmp38 = zext i32 %tmp37 to i64
%tmp31 = bitcast float %B to i32
%tmp32 = zext i32 %tmp31 to i64
%tmp33 = shl i64 %tmp32, 32
%ins35 = or i64 %tmp33, %tmp38
%tmp43 = bitcast i64 %ins35 to <2 x float>
ret <2 x float> %tmp43
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test5(
optimize bitcasts from large integers to vector into vector element insertion from the pieces that feed into the vector. This handles a pattern that occurs frequently due to code generated for the x86-64 abi. We now compile something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.A; ++A.C; return A; } into all nice vector operations: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 12(%rax), %xmm3 pshufd $16, %xmm2, %xmm2 unpcklps %xmm2, %xmm0 addss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 pshufd $16, %xmm3, %xmm2 unpcklps %xmm2, %xmm1 ret instead of icky integer operations: _bar: ## @bar movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 movd %xmm0, %ecx movl 4(%rax), %edx movl 12(%rax), %esi shlq $32, %rdx addq %rcx, %rdx movd %rdx, %xmm0 addss 8(%rax), %xmm1 movd %xmm1, %eax shlq $32, %rsi addq %rax, %rsi movd %rsi, %xmm1 ret This resolves rdar://8360454 llvm-svn: 112343
2010-08-28 09:20:38 +08:00
; CHECK-NEXT: insertelement <2 x float> undef, float %A, i32 0
; CHECK-NEXT: insertelement <2 x float> {{.*}}, float %B, i32 1
Remove trailing whitespace llvm-svn: 174903
2013-02-12 05:36:49 +08:00
; CHECK-NEXT: ret <2 x float>
optimize bitcasts from large integers to vector into vector element insertion from the pieces that feed into the vector. This handles a pattern that occurs frequently due to code generated for the x86-64 abi. We now compile something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.A; ++A.C; return A; } into all nice vector operations: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 12(%rax), %xmm3 pshufd $16, %xmm2, %xmm2 unpcklps %xmm2, %xmm0 addss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 pshufd $16, %xmm3, %xmm2 unpcklps %xmm2, %xmm1 ret instead of icky integer operations: _bar: ## @bar movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 movd %xmm0, %ecx movl 4(%rax), %edx movl 12(%rax), %esi shlq $32, %rdx addq %rcx, %rdx movd %rdx, %xmm0 addss 8(%rax), %xmm1 movd %xmm1, %eax shlq $32, %rsi addq %rax, %rsi movd %rsi, %xmm1 ret This resolves rdar://8360454 llvm-svn: 112343
2010-08-28 09:20:38 +08:00
}
handle the constant case of vector insertion. For something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.B; A.A = 42; return A; } we now generate: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss 12(%rax), %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 unpcklps %xmm0, %xmm1 addss LCPI1_0(%rip), %xmm2 pshufd $16, %xmm2, %xmm2 movss LCPI1_1(%rip), %xmm0 pshufd $16, %xmm0, %xmm0 unpcklps %xmm2, %xmm0 ret instead of: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss 12(%rax), %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 unpcklps %xmm0, %xmm1 addss LCPI1_0(%rip), %xmm2 movd %xmm2, %eax shlq $32, %rax addq $1109917696, %rax ## imm = 0x42280000 movd %rax, %xmm0 ret llvm-svn: 112345
2010-08-28 09:50:57 +08:00
define <2 x float> @test6(float %A){
%tmp23 = bitcast float %A to i32 ; <i32> [#uses=1]
%tmp24 = zext i32 %tmp23 to i64 ; <i64> [#uses=1]
%tmp25 = shl i64 %tmp24, 32 ; <i64> [#uses=1]
%mask20 = or i64 %tmp25, 1109917696 ; <i64> [#uses=1]
%tmp35 = bitcast i64 %mask20 to <2 x float> ; <<2 x float>> [#uses=1]
ret <2 x float> %tmp35
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test6(
handle the constant case of vector insertion. For something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.B; A.A = 42; return A; } we now generate: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss 12(%rax), %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 unpcklps %xmm0, %xmm1 addss LCPI1_0(%rip), %xmm2 pshufd $16, %xmm2, %xmm2 movss LCPI1_1(%rip), %xmm0 pshufd $16, %xmm0, %xmm0 unpcklps %xmm2, %xmm0 ret instead of: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss 12(%rax), %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 unpcklps %xmm0, %xmm1 addss LCPI1_0(%rip), %xmm2 movd %xmm2, %eax shlq $32, %rax addq $1109917696, %rax ## imm = 0x42280000 movd %rax, %xmm0 ret llvm-svn: 112345
2010-08-28 09:50:57 +08:00
; CHECK-NEXT: insertelement <2 x float> <float 4.200000e+01, float undef>, float %A, i32 1
; CHECK: ret
}
Add constant folding support for bitcasts of splat vectors to integers. llvm-svn: 138206
2011-08-20 22:02:29 +08:00
define i64 @ISPC0(i64 %in) {
%out = and i64 %in, xor (i64 bitcast (<4 x i16> <i16 -1, i16 -1, i16 -1, i16 -1> to i64), i64 -1)
ret i64 %out
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @ISPC0(
Add constant folding support for bitcasts of splat vectors to integers. llvm-svn: 138206
2011-08-20 22:02:29 +08:00
; CHECK: ret i64 0
}
Implement Constant::isAllOnesValue(). Fix ConstantFolding to use the new api. llvm-svn: 138469
2011-08-25 04:18:38 +08:00
define i64 @Vec2(i64 %in) {
%out = and i64 %in, xor (i64 bitcast (<4 x i16> <i16 0, i16 0, i16 0, i16 0> to i64), i64 0)
ret i64 %out
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @Vec2(
Implement Constant::isAllOnesValue(). Fix ConstantFolding to use the new api. llvm-svn: 138469
2011-08-25 04:18:38 +08:00
; CHECK: ret i64 0
}
define i64 @All11(i64 %in) {
Remove trailing whitespace llvm-svn: 174903
2013-02-12 05:36:49 +08:00
%out = and i64 %in, xor (i64 bitcast (<2 x float> bitcast (i64 -1 to <2 x float>) to i64), i64 -1)
Implement Constant::isAllOnesValue(). Fix ConstantFolding to use the new api. llvm-svn: 138469
2011-08-25 04:18:38 +08:00
ret i64 %out
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @All11(
Implement Constant::isAllOnesValue(). Fix ConstantFolding to use the new api. llvm-svn: 138469
2011-08-25 04:18:38 +08:00
; CHECK: ret i64 0
}
define i32 @All111(i32 %in) {
Remove trailing whitespace llvm-svn: 174903
2013-02-12 05:36:49 +08:00
%out = and i32 %in, xor (i32 bitcast (<1 x float> bitcast (i32 -1 to <1 x float>) to i32), i32 -1)
Implement Constant::isAllOnesValue(). Fix ConstantFolding to use the new api. llvm-svn: 138469
2011-08-25 04:18:38 +08:00
ret i32 %out
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @All111(
Implement Constant::isAllOnesValue(). Fix ConstantFolding to use the new api. llvm-svn: 138469
2011-08-25 04:18:38 +08:00
; CHECK: ret i32 0
}
Optimization: bitcast (<1 x ...> insertelement ..., X, ...) to ... ==> bitcast X to ... llvm-svn: 174905
2013-02-12 05:41:44 +08:00
define <2 x i16> @BitcastInsert(i32 %a) {
%v = insertelement <1 x i32> undef, i32 %a, i32 0
%r = bitcast <1 x i32> %v to <2 x i16>
ret <2 x i16> %r
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @BitcastInsert(
Optimization: bitcast (<1 x ...> insertelement ..., X, ...) to ... ==> bitcast X to ... llvm-svn: 174905
2013-02-12 05:41:44 +08:00
; CHECK: bitcast i32 %a to <2 x i16>
}
InstCombine: Don't allow turning vector-of-pointer loads into vector-of-integer. The code below can't handle any pointers. PR17293. llvm-svn: 191036
2013-09-20 04:59:04 +08:00
; PR17293
define <2 x i64> @test7(<2 x i8*>* %arg) nounwind {
%cast = bitcast <2 x i8*>* %arg to <2 x i64>*
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%load = load <2 x i64>, <2 x i64>* %cast, align 16
InstCombine: Don't allow turning vector-of-pointer loads into vector-of-integer. The code below can't handle any pointers. PR17293. llvm-svn: 191036
2013-09-20 04:59:04 +08:00
ret <2 x i64> %load
; CHECK: @test7
; CHECK: bitcast
; CHECK: load
}